Application of GPU Computing to Some Urban Traffic Problems
Autor(a) principal: | |
---|---|
Data de Publicação: | 2016 |
Tipo de documento: | Tese |
Idioma: | por |
Título da fonte: | Repositório Institucional da UFG |
Texto Completo: | http://repositorio.bc.ufg.br/tede/handle/tede/6695 |
Resumo: | The present work studies and proposes GPU-based parallel algorithms and implementations for the problem of macroscopic assignment of urban traffic on large-scale networks, promoting an in-depth investigation on each sub-problem that must be efficiently solved during the traffic assignment process. Among the main contributions of this work, there are: 1) the first GPU-based algorithm for the enumeration of chordless cycles; 2) a new parallel GPU-based shortest path algorithm that takes advantage of some common properties of urban traffic networks; a refinement in the parallel reduction implementation proposed by one of the leaders in the GPU market, which resulted in a 2.8x speedup relative to its original version; and finally, 3) a parallel algorithm for the macroscopic traffic assignment problem, 39x faster than the equivalent sequential approach when applied to large scale networks. The main goal of this thesis is to contribute to the extension of the PET-Gyn software, proposing efficient GPU data structures and parallel algorithms for a faster resolution of two well known problems in the literature: The Traffic Assignment Problem (TAP) and the Enumeration of Chordless Cycles. When applied to difficult input sets, the performed experiments showed a clear advantage of the parallel algorithms over their sequential versions. |
id |
UFG-2_d71c74cf1e267755cbb9757827de4a20 |
---|---|
oai_identifier_str |
oai:repositorio.bc.ufg.br:tede/6695 |
network_acronym_str |
UFG-2 |
network_name_str |
Repositório Institucional da UFG |
repository_id_str |
|
spelling |
Nascimento, Hugo Alexandre Dantas dohttp://lattes.cnpq.br/2920005922426876Martins, Wellington Santoshttp://lattes.cnpq.br/3041686206689904Camponogara, EduardoClua, Esteban Walter GonzalezMongelli , HenriqueCosta, Fábio Moreirahttp://lattes.cnpq.br/6868170610194494Jradi, Walid Abdala Rfaei2017-01-09T09:29:25Z2016-11-30JRADI, Walid Abdala Rfaei. Application of GPU Computing to Some Urban Traffic Problems. 2016. 195 f. Tese (Doutorado em Ciência da Computação em Rede) - Universidade Federal de Goiás, Goiânia, 2016.http://repositorio.bc.ufg.br/tede/handle/tede/6695The present work studies and proposes GPU-based parallel algorithms and implementations for the problem of macroscopic assignment of urban traffic on large-scale networks, promoting an in-depth investigation on each sub-problem that must be efficiently solved during the traffic assignment process. Among the main contributions of this work, there are: 1) the first GPU-based algorithm for the enumeration of chordless cycles; 2) a new parallel GPU-based shortest path algorithm that takes advantage of some common properties of urban traffic networks; a refinement in the parallel reduction implementation proposed by one of the leaders in the GPU market, which resulted in a 2.8x speedup relative to its original version; and finally, 3) a parallel algorithm for the macroscopic traffic assignment problem, 39x faster than the equivalent sequential approach when applied to large scale networks. The main goal of this thesis is to contribute to the extension of the PET-Gyn software, proposing efficient GPU data structures and parallel algorithms for a faster resolution of two well known problems in the literature: The Traffic Assignment Problem (TAP) and the Enumeration of Chordless Cycles. When applied to difficult input sets, the performed experiments showed a clear advantage of the parallel algorithms over their sequential versions.O presente trabalho estuda e propõe algoritmos e implementações paralelas baseadas em GPU para o problema de alocação macroscópica de tráfego urbano em redes de grande porte, promovendo uma investigação aprofundada de cada sub-problema que deve ser resolvido de forma eficiente durante o processo de atribuição de tráfego. Entre as principais contribuições deste trabalho, estão: 1) o primeiro algoritmo baseado em GPU para a enumeração de ciclos sem corda; 2) um novo algoritmo de caminho mínimo paralelo que tira vantagem de algumas propriedades comuns das redes de tráfego urbano; Um refinamento na implementação de redução paralela proposta por um dos líderes no mercado de GPU, o que resultou em uma aceleração de 2,8x em relação à sua versão original; 3) e, finalmente, um algoritmo paralelo para o problema de alocação macroscópica de tráfego, 39x mais rápido do que a abordagem equivalente sequencial quando aplicado a redes de larga escala. O objetivo principal desta tese é de contribuir para a expansão do software PET-Gyn, propondo estruturas de dados de GPU eficientes e algoritmos paralelos para uma resolução mais rápida de dois problemas bem conhecidos na literatura: O Problema de Alocação de Tráfego e a Enumeração de Ciclos sem Corda. Quando aplicados a conjuntos de entrada difíceis, os experimentos realizados mostraram uma clara vantagem dos algoritmos paralelos sobre suas versões sequenciais.Submitted by Erika Demachki (erikademachki@gmail.com) on 2017-01-06T16:59:11Z No. of bitstreams: 2 Tese - Walid Abdala Rfaei Jradi - 2016.pdf: 5339936 bytes, checksum: 0a0a6bdc4791ee31c229b5175ae3af03 (MD5) license_rdf: 0 bytes, checksum: d41d8cd98f00b204e9800998ecf8427e (MD5)Approved for entry into archive by Luciana Ferreira (lucgeral@gmail.com) on 2017-01-09T09:29:25Z (GMT) No. of bitstreams: 2 Tese - Walid Abdala Rfaei Jradi - 2016.pdf: 5339936 bytes, checksum: 0a0a6bdc4791ee31c229b5175ae3af03 (MD5) license_rdf: 0 bytes, checksum: d41d8cd98f00b204e9800998ecf8427e (MD5)Made available in DSpace on 2017-01-09T09:29:25Z (GMT). No. of bitstreams: 2 Tese - Walid Abdala Rfaei Jradi - 2016.pdf: 5339936 bytes, checksum: 0a0a6bdc4791ee31c229b5175ae3af03 (MD5) license_rdf: 0 bytes, checksum: d41d8cd98f00b204e9800998ecf8427e (MD5) Previous issue date: 2016-11-30Coordenação de Aperfeiçoamento de Pessoal de Nível Superior - CAPESapplication/pdfporUniversidade Federal de GoiásPrograma de Pós-graduação em Ciência da Computação (INF)UFGBrasilInstituto de Informática - INF (RG)http://creativecommons.org/licenses/by-nc-nd/4.0/info:eu-repo/semantics/openAccessTráfego urbanoAlocação macroscópica de tráfegoComputação paralelaGPUUrban trafficMacroscopic traffic assignmentParallel computingCIENCIAS EXATAS E DA TERRA::CIENCIA DA COMPUTACAOApplication of GPU Computing to Some Urban Traffic Problemsinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/doctoralThesis-3303550325223384799600600600600-771226673463364476836717112058112045092075167498588264571reponame:Repositório Institucional da UFGinstname:Universidade Federal de Goiás (UFG)instacron:UFGLICENSElicense.txtlicense.txttext/plain; charset=utf-82165http://repositorio.bc.ufg.br/tede/bitstreams/d0852846-c187-4481-9edf-e4cea112b35d/downloadbd3efa91386c1718a7f26a329fdcb468MD51CC-LICENSElicense_urllicense_urltext/plain; charset=utf-849http://repositorio.bc.ufg.br/tede/bitstreams/07702037-af98-43c6-afdd-4abae3814100/download4afdbb8c545fd630ea7db775da747b2fMD52license_textlicense_texttext/html; charset=utf-80http://repositorio.bc.ufg.br/tede/bitstreams/b95c7198-c8df-4061-b5a5-86bbc0a23f6d/downloadd41d8cd98f00b204e9800998ecf8427eMD53license_rdflicense_rdfapplication/rdf+xml; charset=utf-80http://repositorio.bc.ufg.br/tede/bitstreams/a73f88ae-c0e2-4acc-b1ab-e905019744a4/downloadd41d8cd98f00b204e9800998ecf8427eMD54ORIGINALTese - Walid Abdala Rfaei Jradi - 2016.pdfTese - Walid Abdala Rfaei Jradi - 2016.pdfapplication/pdf5339936http://repositorio.bc.ufg.br/tede/bitstreams/bbc47b63-2719-407d-b8ed-16b688964e12/download0a0a6bdc4791ee31c229b5175ae3af03MD55tede/66952019-06-27 09:31:41.863http://creativecommons.org/licenses/by-nc-nd/4.0/Acesso Abertoopen.accessoai:repositorio.bc.ufg.br:tede/6695http://repositorio.bc.ufg.br/tedeRepositório InstitucionalPUBhttp://repositorio.bc.ufg.br/oai/requesttasesdissertacoes.bc@ufg.bropendoar:2019-06-27T12:31:41Repositório Institucional da UFG - Universidade Federal de Goiás (UFG)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 |
dc.title.por.fl_str_mv |
Application of GPU Computing to Some Urban Traffic Problems |
title |
Application of GPU Computing to Some Urban Traffic Problems |
spellingShingle |
Application of GPU Computing to Some Urban Traffic Problems Jradi, Walid Abdala Rfaei Tráfego urbano Alocação macroscópica de tráfego Computação paralela GPU Urban traffic Macroscopic traffic assignment Parallel computing CIENCIAS EXATAS E DA TERRA::CIENCIA DA COMPUTACAO |
title_short |
Application of GPU Computing to Some Urban Traffic Problems |
title_full |
Application of GPU Computing to Some Urban Traffic Problems |
title_fullStr |
Application of GPU Computing to Some Urban Traffic Problems |
title_full_unstemmed |
Application of GPU Computing to Some Urban Traffic Problems |
title_sort |
Application of GPU Computing to Some Urban Traffic Problems |
author |
Jradi, Walid Abdala Rfaei |
author_facet |
Jradi, Walid Abdala Rfaei |
author_role |
author |
dc.contributor.advisor1.fl_str_mv |
Nascimento, Hugo Alexandre Dantas do |
dc.contributor.advisor1Lattes.fl_str_mv |
http://lattes.cnpq.br/2920005922426876 |
dc.contributor.advisor-co1.fl_str_mv |
Martins, Wellington Santos |
dc.contributor.advisor-co1Lattes.fl_str_mv |
http://lattes.cnpq.br/3041686206689904 |
dc.contributor.referee1.fl_str_mv |
Camponogara, Eduardo |
dc.contributor.referee2.fl_str_mv |
Clua, Esteban Walter Gonzalez |
dc.contributor.referee3.fl_str_mv |
Mongelli , Henrique |
dc.contributor.referee4.fl_str_mv |
Costa, Fábio Moreira |
dc.contributor.authorLattes.fl_str_mv |
http://lattes.cnpq.br/6868170610194494 |
dc.contributor.author.fl_str_mv |
Jradi, Walid Abdala Rfaei |
contributor_str_mv |
Nascimento, Hugo Alexandre Dantas do Martins, Wellington Santos Camponogara, Eduardo Clua, Esteban Walter Gonzalez Mongelli , Henrique Costa, Fábio Moreira |
dc.subject.por.fl_str_mv |
Tráfego urbano Alocação macroscópica de tráfego Computação paralela GPU |
topic |
Tráfego urbano Alocação macroscópica de tráfego Computação paralela GPU Urban traffic Macroscopic traffic assignment Parallel computing CIENCIAS EXATAS E DA TERRA::CIENCIA DA COMPUTACAO |
dc.subject.eng.fl_str_mv |
Urban traffic Macroscopic traffic assignment Parallel computing |
dc.subject.cnpq.fl_str_mv |
CIENCIAS EXATAS E DA TERRA::CIENCIA DA COMPUTACAO |
description |
The present work studies and proposes GPU-based parallel algorithms and implementations for the problem of macroscopic assignment of urban traffic on large-scale networks, promoting an in-depth investigation on each sub-problem that must be efficiently solved during the traffic assignment process. Among the main contributions of this work, there are: 1) the first GPU-based algorithm for the enumeration of chordless cycles; 2) a new parallel GPU-based shortest path algorithm that takes advantage of some common properties of urban traffic networks; a refinement in the parallel reduction implementation proposed by one of the leaders in the GPU market, which resulted in a 2.8x speedup relative to its original version; and finally, 3) a parallel algorithm for the macroscopic traffic assignment problem, 39x faster than the equivalent sequential approach when applied to large scale networks. The main goal of this thesis is to contribute to the extension of the PET-Gyn software, proposing efficient GPU data structures and parallel algorithms for a faster resolution of two well known problems in the literature: The Traffic Assignment Problem (TAP) and the Enumeration of Chordless Cycles. When applied to difficult input sets, the performed experiments showed a clear advantage of the parallel algorithms over their sequential versions. |
publishDate |
2016 |
dc.date.issued.fl_str_mv |
2016-11-30 |
dc.date.accessioned.fl_str_mv |
2017-01-09T09:29:25Z |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/doctoralThesis |
format |
doctoralThesis |
status_str |
publishedVersion |
dc.identifier.citation.fl_str_mv |
JRADI, Walid Abdala Rfaei. Application of GPU Computing to Some Urban Traffic Problems. 2016. 195 f. Tese (Doutorado em Ciência da Computação em Rede) - Universidade Federal de Goiás, Goiânia, 2016. |
dc.identifier.uri.fl_str_mv |
http://repositorio.bc.ufg.br/tede/handle/tede/6695 |
identifier_str_mv |
JRADI, Walid Abdala Rfaei. Application of GPU Computing to Some Urban Traffic Problems. 2016. 195 f. Tese (Doutorado em Ciência da Computação em Rede) - Universidade Federal de Goiás, Goiânia, 2016. |
url |
http://repositorio.bc.ufg.br/tede/handle/tede/6695 |
dc.language.iso.fl_str_mv |
por |
language |
por |
dc.relation.program.fl_str_mv |
-3303550325223384799 |
dc.relation.confidence.fl_str_mv |
600 600 600 600 |
dc.relation.department.fl_str_mv |
-7712266734633644768 |
dc.relation.cnpq.fl_str_mv |
3671711205811204509 |
dc.relation.sponsorship.fl_str_mv |
2075167498588264571 |
dc.rights.driver.fl_str_mv |
http://creativecommons.org/licenses/by-nc-nd/4.0/ info:eu-repo/semantics/openAccess |
rights_invalid_str_mv |
http://creativecommons.org/licenses/by-nc-nd/4.0/ |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
application/pdf |
dc.publisher.none.fl_str_mv |
Universidade Federal de Goiás |
dc.publisher.program.fl_str_mv |
Programa de Pós-graduação em Ciência da Computação (INF) |
dc.publisher.initials.fl_str_mv |
UFG |
dc.publisher.country.fl_str_mv |
Brasil |
dc.publisher.department.fl_str_mv |
Instituto de Informática - INF (RG) |
publisher.none.fl_str_mv |
Universidade Federal de Goiás |
dc.source.none.fl_str_mv |
reponame:Repositório Institucional da UFG instname:Universidade Federal de Goiás (UFG) instacron:UFG |
instname_str |
Universidade Federal de Goiás (UFG) |
instacron_str |
UFG |
institution |
UFG |
reponame_str |
Repositório Institucional da UFG |
collection |
Repositório Institucional da UFG |
bitstream.url.fl_str_mv |
http://repositorio.bc.ufg.br/tede/bitstreams/d0852846-c187-4481-9edf-e4cea112b35d/download http://repositorio.bc.ufg.br/tede/bitstreams/07702037-af98-43c6-afdd-4abae3814100/download http://repositorio.bc.ufg.br/tede/bitstreams/b95c7198-c8df-4061-b5a5-86bbc0a23f6d/download http://repositorio.bc.ufg.br/tede/bitstreams/a73f88ae-c0e2-4acc-b1ab-e905019744a4/download http://repositorio.bc.ufg.br/tede/bitstreams/bbc47b63-2719-407d-b8ed-16b688964e12/download |
bitstream.checksum.fl_str_mv |
bd3efa91386c1718a7f26a329fdcb468 4afdbb8c545fd630ea7db775da747b2f d41d8cd98f00b204e9800998ecf8427e d41d8cd98f00b204e9800998ecf8427e 0a0a6bdc4791ee31c229b5175ae3af03 |
bitstream.checksumAlgorithm.fl_str_mv |
MD5 MD5 MD5 MD5 MD5 |
repository.name.fl_str_mv |
Repositório Institucional da UFG - Universidade Federal de Goiás (UFG) |
repository.mail.fl_str_mv |
tasesdissertacoes.bc@ufg.br |
_version_ |
1798044389617958912 |