Parallel prefix operations on GPU: tridiagonal system solvers and scan operators

Simple item page
UDC.coleccionInvestigaciónes_ES
UDC.departamentoEnxeñaría de Computadoreses_ES
UDC.endPage1523es_ES
UDC.grupoInvGrupo de Arquitectura de Computadores (GAC)es_ES
UDC.journalTitleJournal of Supercomputinges_ES
UDC.startPage1510es_ES
UDC.volume75es_ES
dc.contributor.authorPérez Diéguez, Adrián
dc.contributor.authorAmor, Margarita
dc.contributor.authorDoallo, Ramón
dc.date.accessioned2025-01-21T09:13:50Z
dc.date.available2025-01-21T09:13:50Z
dc.date.issued2019
dc.descriptionThis version of the article has been accepted for publication, after peer review (when applicable) and is subject to Springer Nature’s AM terms of use, but is not the Version of Record and does not reflect post-acceptance improvements, or any corrections. The Version of Record is available online at: http://dx.doi.org/10.1007/s11227-018-2676-zes_ES
dc.description.abstract[Abstract]: Modern GPUs can achieve high computing power at low cost, but still requires much time and effort. Tridiagonal system and scan solvers are one example of widely used algorithms which can take advantage of these devices. In this article, one tridiagonal system solver and two scan primitive operators are implemented on CUDA GPUs. To do so, a tuning strategy based on three phases is developed. Additionally, a performance analysis is performed for two different CUDA GPU architectures, resulting in a huge improvement with respect to the state of the art.es_ES
dc.description.sponsorshipThis work is supported by the Ministry of Economy and Competitiveness of Spain, TIN2016-75845-P (AEI/FEDER, UE), by the Galician Government and FEDER funds under the Consolidation Program of Competitive Reference Groups (GRC2013-055) as well as under the Consolidation Programme of Competitive Research Units [Ref. R2014/049 and Ref. R2016/037]; and by the FPU Program of the Ministry of Education of Spain (FPU14/02801).es_ES
dc.description.sponsorshipXunta de Galicia; GRC2013/055es_ES
dc.description.sponsorshipXunta de Galicia; R2014/049es_ES
dc.description.sponsorshipXunta de Galicia; R2016/037es_ES
dc.identifier.citationDiéguez, A.P., Amor, M. & Doallo, R. Parallel prefix operations on GPU: tridiagonal system solvers and scan operators. J Supercomput 75, 1510–1523 (2019). https://doi.org/10.1007/s11227-018-2676-zes_ES
dc.identifier.doi10.1007/s11227-018-2676-z
dc.identifier.issn0920-8542
dc.identifier.urihttp://hdl.handle.net/2183/40804
dc.language.isoenges_ES
dc.publisherSpringer New York LLCes_ES
dc.relation.projectIDinfo:eu-repo/grantAgreement/MINECO/Plan Estatal de Investigación Científica y Técnica y de Innovación 2013-2016/TIN2016-75845-P/ES/NUEVOS DESAFIOS EN COMPUTACION DE ALTAS PRESTACIONES: DESDE ARQUITECTURAS HASTA APLICACIONES (II)es_ES
dc.relation.projectIDinfo:eu-repo/grantAgreement/MECD/Programa Estatal de Promoción del Talento y su Empleabilidad/FPU14%2F02801/ES/es_ES
dc.relation.urihttps://doi.org/10.1007/s11227-018-2676-zes_ES
dc.rightsCopyright © 2018, Springer Science Business Media, LLC, part of Springer Naturees_ES
dc.rights.accessRightsopen accesses_ES
dc.subjectCUDAes_ES
dc.subjectGPUes_ES
dc.subjectScanes_ES
dc.subjectTridiagonal systemses_ES
dc.subjectTuninges_ES
dc.titleParallel prefix operations on GPU: tridiagonal system solvers and scan operatorses_ES
dc.typejournal articlees_ES
dspace.entity.typePublication
relation.isAuthorOfPublication31d7c9d0-70ef-44ef-af1d-e40f560c41bc
relation.isAuthorOfPublicationc98c1fe1-2016-44c1-9225-43fe1c6b8088
relation.isAuthorOfPublicationb3302f65-05d3-4b2c-b8b3-8503e58bba5e
relation.isAuthorOfPublication.latestForDiscovery31d7c9d0-70ef-44ef-af1d-e40f560c41bc

Files

Original bundle

Now showing 1 - 1 of 1
Thumbnail Image
Name:
Amor_Margarita_2019_Parallel_prefix_operations_on_GPU_tridiagonal_system_solvers_and_scan_operators.pdf
Size:
1.05 MB
Format:
Adobe Portable Document Format
Description:
Versión aceptada
Download

Collections

Investigación (FIC)