Please use this identifier to cite or link to this item: http://repositorio.unicamp.br/jspui/handle/REPOSIP/351034
Full metadata record
DC FieldValueLanguage
dc.contributor.CRUESPUNIVERSIDADE ESTADUAL DE CAMPINASpt_BR
dc.contributor.authorunicampValle, Eduardo-
dc.contributor.authorunicampTorres, Ricardo da Silva-
dc.typeArtigopt_BR
dc.titleApproximate similarity search for online multimedia services on distributed CPU-GPU platformspt_BR
dc.contributor.authorMariano, N.-
dc.contributor.authorTorres, R.-
dc.contributor.authorTeodoro, G.-
dc.contributor.authorValle, E.-
dc.contributor.authorMeira, W.-
dc.contributor.authorSaltz, J. H.-
dc.subjectIndexaçãopt_BR
dc.subjectBanco de dadospt_BR
dc.subject.otherlanguageIndexingpt_BR
dc.subject.otherlanguageDatabasespt_BR
dc.description.abstractSimilarity search in high-dimensional spaces is a pivotal operation for several database applications, including online content-based multimedia services. With the increasing popularity of multimedia applications, these services are facing new challenges regarding (1) the very large and growing volumes of data to be indexed/searched and (2) the necessity of reducing the response times as observed by end-users. In addition, the nature of the interactions between users and online services creates fluctuating query request rates throughout execution, which requires a similarity search engine to adapt to better use the computation platform and minimize response times. In this work, we address these challenges with Hypercurves, a flexible framework for answering approximate k-nearest neighbor (kNN) queries for very large multimedia databases. Hypercurves executes in hybrid CPU-GPU environments and is able to attain massive query-processing rates through the cooperative use of these devices. Hypercurves also changes its CPU-GPU task partitioning dynamically according to the observed load, aiming for optimal response times. In our empirical evaluation, dynamic task partitioning reduced query response times by approximately 50 % compared to the best static task partition. Due to a probabilistic proof of equivalence to the sequential kNN algorithm, the CPU-GPU execution of Hypercurves in distributed (multi-node) environments can be aggressively optimized, attaining superlinear scalability while still guaranteeing, with high probability, results at least as good as those from the sequential algorithmpt_BR
dc.relation.ispartofThe VLDB Journalpt_BR
dc.publisher.cityNew York, NYpt_BR
dc.publisher.countryEstados Unidospt_BR
dc.publisherAssociation for Computing Machinerypt_BR
dc.date.issued2014-
dc.date.monthofcirculationJunept_BR
dc.language.isoengpt_BR
dc.description.volume23pt_BR
dc.description.issuenumber3pt_BR
dc.description.firstpage427pt_BR
dc.description.lastpage448pt_BR
dc.rightsFechadopt_BR
dc.sourceWOSpt_BR
dc.identifier.issn1066-8888pt_BR
dc.identifier.eissn0949-877Xpt_BR
dc.identifier.doi10.1007/s00778-013-0329-7pt_BR
dc.identifier.urlhttps://link.springer.com/article/10.1007/s00778-013-0329-7pt_BR
dc.description.sponsorshipCONSELHO NACIONAL DE DESENVOLVIMENTO CIENTÍFICO E TECNOLÓGICO - CNPQpt_BR
dc.description.sponsorshipCOORDENAÇÃO DE APERFEIÇOAMENTO DE PESSOAL DE NÍVEL SUPERIOR - CAPESpt_BR
dc.description.sponsorshipFUNDAÇÃO DE AMPARO À PESQUISA DO ESTADO DE MINAS GERAIS - FAPEMIGpt_BR
dc.description.sponsorshipFUNDAÇÃO DE AMPARO À PESQUISA DO ESTADO DE SÃO PAULO - FAPESPpt_BR
dc.description.sponsordocumentnumber306580/2012-8; 484254/2012-0pt_BR
dc.description.sponsordocumentnumbersem informaçãopt_BR
dc.description.sponsordocumentnumbersem informaçãopt_BR
dc.description.sponsordocumentnumbersem informaçãopt_BR
dc.date.available2020-10-14T17:58:27Z-
dc.date.accessioned2020-10-14T17:58:27Z-
dc.description.provenanceSubmitted by Cintia Oliveira de Moura (cintiaom@unicamp.br) on 2020-10-14T17:58:27Z No. of bitstreams: 0en
dc.description.provenanceMade available in DSpace on 2020-10-14T17:58:27Z (GMT). No. of bitstreams: 0 Previous issue date: 2014en
dc.identifier.urihttp://repositorio.unicamp.br/jspui/handle/REPOSIP/351034-
dc.contributor.departmentDepartamento de Engenharia de Computação e Automação Industrialpt_BR
dc.contributor.departmentDepartamento de Sistemas de Informaçãopt_BR
dc.contributor.unidadeFaculdade de Engenharia Elétrica e da Computaçãopt_BR
dc.contributor.unidadeInstituto de Computaçãopt_BR
dc.subject.keywordInformation retrievalpt_BR
dc.subject.keywordHypercurvespt_BR
dc.identifier.source000336383300004pt_BR
dc.creator.orcid0000-0001-5396-9868pt_BR
dc.creator.orcid0000-0001-9772-263Xpt_BR
dc.type.formArtigopt_BR
dc.description.sponsorNoteInWeb; National Science Foundation (NSF)pt_BR
Appears in Collections:IC - Artigos e Outros Documentos
FEEC - Artigos e Outros Documentos

Files in This Item:
There are no files associated with this item.


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.