F-MPJ: scalable Java message-passing communications on parallel systems

UDC.coleccionInvestigaciónes_ES
UDC.departamentoEnxeñaría de Computadoreses_ES
UDC.endPage140es_ES
UDC.grupoInvGrupo de Arquitectura de Computadores (GAC)es_ES
UDC.issue1es_ES
UDC.journalTitleThe Journal of Supercomputinges_ES
UDC.startPage117es_ES
UDC.volume60es_ES
dc.contributor.authorTaboada, Guillermo L.
dc.contributor.authorTouriño, Juan
dc.contributor.authorDoallo, Ramón
dc.date.accessioned2019-02-28T18:27:31Z
dc.date.available2019-02-28T18:27:31Z
dc.date.issued2012-04
dc.descriptionThis is a post-peer-review, pre-copyedit version of an article published in The Journal of Supercomputing. The final authenticated version is available online at: https://doi.org/10.1007/s11227-009-0270-0es_ES
dc.description.abstract[Abstract] This paper presents F-MPJ (Fast MPJ), a scalable and efficient Message-Passing in Java (MPJ) communication middleware for parallel computing. The increasing interest in Java as the programming language of the multi-core era demands scalable performance on hybrid architectures (with both shared and distributed memory spaces). However, current Java communication middleware lacks efficient communication support. F-MPJ boosts this situation by: (1) providing efficient non-blocking communication, which allows communication overlapping and thus scalable performance; (2) taking advantage of shared memory systems and high-performance networks through the use of our high-performance Java sockets implementation (named JFS, Java Fast Sockets); (3) avoiding the use of communication buffers; and (4) optimizing MPJ collective primitives. Thus, F-MPJ significantly improves the scalability of current MPJ implementations. A performance evaluation on an InfiniBand multi-core cluster has shown that F-MPJ communication primitives outperform representative MPJ libraries up to 60 times. Furthermore, the use of F-MPJ in communication-intensive MPJ codes has increased their performance up to seven times.es_ES
dc.description.sponsorshipMinisterio de Educación y Ciencia; TIN2004-07797-C02es_ES
dc.description.sponsorshipMinisterio de Educación y Ciencia; TIN2007-67537-C03-2es_ES
dc.description.sponsorshipXunta de Galicia; PGIDIT06PXIB105228PRes_ES
dc.identifier.citationTaboada, G.L., Touriño, J. & Doallo, R. J Supercomput (2012) 60: 117. https://doi.org/10.1007/s11227-009-0270-0es_ES
dc.identifier.doi10.1007/s11227-009-0270-0
dc.identifier.issn0920-8542
dc.identifier.issn1573-0484
dc.identifier.urihttp://hdl.handle.net/2183/22023
dc.language.isoenges_ES
dc.publisherSpringer New York LLCes_ES
dc.relation.urihttps://doi.org/10.1007/s11227-009-0270-0es_ES
dc.rights.accessRightsopen accesses_ES
dc.subjectMessage-Passing in Java (MPJ)es_ES
dc.subjectScalable parallel systemses_ES
dc.subjectCommunication middlewarees_ES
dc.subjectScalable collective communicationes_ES
dc.subjectHigh-performance computinges_ES
dc.subjectPerformance evaluationes_ES
dc.titleF-MPJ: scalable Java message-passing communications on parallel systemses_ES
dc.typejournal articlees_ES
dspace.entity.typePublication
relation.isAuthorOfPublication86e306a5-99a1-4c43-8faa-720f0a9f0a34
relation.isAuthorOfPublicationb3302f65-05d3-4b2c-b8b3-8503e58bba5e
relation.isAuthorOfPublication.latestForDiscovery86e306a5-99a1-4c43-8faa-720f0a9f0a34

Files

Original bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
G.L.Taboada_2012_F-MPJ_scalable_Java_message-passing_communications_on_parallel_systems.pdf
Size:
892.65 KB
Format:
Adobe Portable Document Format
Description: