Mostra el registre d'ítem simple

dc.contributor.authorPlanas, Judit
dc.contributor.authorBadia Sala, Rosa Maria
dc.contributor.authorAyguadé Parra, Eduard
dc.contributor.authorLabarta Mancho, Jesús José
dc.contributor.otherUniversitat Politècnica de Catalunya. Departament d'Arquitectura de Computadors
dc.date.accessioned2017-05-10T11:30:07Z
dc.date.available2017-05-10T11:30:07Z
dc.date.issued2015
dc.identifier.citationPlanas, J., Badia, R.M., Ayguadé, E., Labarta, J. AMA: asynchronous management of accelerators for task-based programming models. A: International Conference on Computational Science. "Procedia Computer Science (Vol. 51, 2015)". Reykjavík: Elsevier, 2015, p. 130-139.
dc.identifier.isbn1877-0509
dc.identifier.urihttp://hdl.handle.net/2117/104266
dc.description.abstractComputational science has benefited in the last years from emerging accelerators that increase the performance of scientific simulations, but using these devices hinders the programming task. This paper presents AMA: a set of optimization techniques to efficiently manage multi-accelerator systems. AMA maximizes the overlap of computation and communication in a blocking-free way. Then, we can use such spare time to do other work while waiting for device operations. Implemented on top of a task-based framework, the experimental evaluation of AMA on a quad-GPU node shows that we reach the performance of a hand-tuned native CUDA code, with the advantage of fully hiding the device management. In addition, we obtain up to more than 2x performance speed-up with respect to the original framework implementation.
dc.format.extent10 p.
dc.language.isoeng
dc.publisherElsevier
dc.rightsAttribution-NonCommercial-NoDerivs 3.0 Spain
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/3.0/es/
dc.subjectÀrees temàtiques de la UPC::Informàtica::Arquitectura de computadors
dc.subject.lcshGraphics processing units
dc.subject.lcshMultiprocessors
dc.subject.lcshParallel processing (Electronic computers)
dc.subject.otherAccelerator management
dc.subject.otherAsynchronous devices
dc.subject.otherProgramming models
dc.subject.otherMulti-GPU systems
dc.titleAMA: asynchronous management of accelerators for task-based programming models
dc.typeConference report
dc.subject.lemacMultiprocessadors
dc.subject.lemacProcessament en paral·lel (Ordinadors)
dc.contributor.groupUniversitat Politècnica de Catalunya. CAP - Grup de Computació d'Altes Prestacions
dc.identifier.doi10.1016/j.procs.2015.05.212
dc.description.peerreviewedPeer Reviewed
dc.relation.publisherversionhttp://www.sciencedirect.com/science/article/pii/S1877050915010200
dc.rights.accessOpen Access
local.identifier.drac19376613
dc.description.versionPostprint (published version)
local.citation.authorPlanas, J.; Badia, R.M.; Ayguadé, E.; Labarta, J.
local.citation.contributorInternational Conference on Computational Science
local.citation.pubplaceReykjavík
local.citation.publicationNameProcedia Computer Science (Vol. 51, 2015)
local.citation.startingPage130
local.citation.endingPage139


Fitxers d'aquest items

Thumbnail

Aquest ítem apareix a les col·leccions següents

Mostra el registre d'ítem simple