{"id":"https://openalex.org/W2548529098","doi":"https://doi.org/10.1155/2017/1205892","title":"Performance Optimization of 3D Lattice Boltzmann Flow Solver on a GPU","display_name":"Performance Optimization of 3D Lattice Boltzmann Flow Solver on a GPU","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2548529098","doi":"https://doi.org/10.1155/2017/1205892","mag":"2548529098"},"language":"en","primary_location":{"id":"doi:10.1155/2017/1205892","is_oa":true,"landing_page_url":"https://doi.org/10.1155/2017/1205892","pdf_url":"http://downloads.hindawi.com/journals/sp/2017/1205892.pdf","source":{"id":"https://openalex.org/S166774750","display_name":"Scientific Programming","issn_l":"1058-9244","issn":["1058-9244","1875-919X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319869","host_organization_name":"Hindawi Publishing Corporation","host_organization_lineage":["https://openalex.org/P4310319869"],"host_organization_lineage_names":["Hindawi Publishing Corporation"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Scientific Programming","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"http://downloads.hindawi.com/journals/sp/2017/1205892.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5057707318","display_name":"Nhat-Phuong Tran","orcid":"https://orcid.org/0000-0002-4374-9068"},"institutions":[{"id":"https://openalex.org/I89440247","display_name":"Myongji University","ror":"https://ror.org/00s9dpb54","country_code":"KR","type":"education","lineage":["https://openalex.org/I89440247"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Nhat-Phuong Tran","raw_affiliation_strings":["Department of Computer Science and Engineering, Myongji University, 116 Myongji-ro, Cheoin-gu, Yongin, Gyeonggi-do, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Myongji University, 116 Myongji-ro, Cheoin-gu, Yongin, Gyeonggi-do, Republic of Korea","institution_ids":["https://openalex.org/I89440247"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101699334","display_name":"Myungho Lee","orcid":"https://orcid.org/0000-0003-4383-6425"},"institutions":[{"id":"https://openalex.org/I89440247","display_name":"Myongji University","ror":"https://ror.org/00s9dpb54","country_code":"KR","type":"education","lineage":["https://openalex.org/I89440247"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Myungho Lee","raw_affiliation_strings":["Department of Computer Science and Engineering, Myongji University, 116 Myongji-ro, Cheoin-gu, Yongin, Gyeonggi-do, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Myongji University, 116 Myongji-ro, Cheoin-gu, Yongin, Gyeonggi-do, Republic of Korea","institution_ids":["https://openalex.org/I89440247"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050329084","display_name":"Sugwon Hong","orcid":"https://orcid.org/0000-0002-6184-9310"},"institutions":[{"id":"https://openalex.org/I89440247","display_name":"Myongji University","ror":"https://ror.org/00s9dpb54","country_code":"KR","type":"education","lineage":["https://openalex.org/I89440247"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sugwon Hong","raw_affiliation_strings":["Department of Computer Science and Engineering, Myongji University, 116 Myongji-ro, Cheoin-gu, Yongin, Gyeonggi-do, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Myongji University, 116 Myongji-ro, Cheoin-gu, Yongin, Gyeonggi-do, Republic of Korea","institution_ids":["https://openalex.org/I89440247"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101699334"],"corresponding_institution_ids":["https://openalex.org/I89440247"],"apc_list":{"value":1800,"currency":"USD","value_usd":1800},"apc_paid":{"value":1800,"currency":"USD","value_usd":1800},"fwci":3.4569,"has_fulltext":true,"cited_by_count":41,"citation_normalized_percentile":{"value":0.92103789,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"2017","issue":null,"first_page":"1","last_page":"16"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11751","display_name":"Lattice Boltzmann Simulation Studies","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11751","display_name":"Lattice Boltzmann Simulation Studies","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9728000164031982,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9635999798774719,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.9088395833969116},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.855232834815979},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.6592686772346497},{"id":"https://openalex.org/keywords/solver","display_name":"Solver","score":0.6095309257507324},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.6029614806175232},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.5674272775650024},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.5134838223457336},{"id":"https://openalex.org/keywords/lattice-boltzmann-methods","display_name":"Lattice Boltzmann methods","score":0.5067158341407776},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.46135497093200684},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.40969976782798767},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.23390674591064453},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.08975014090538025}],"concepts":[{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.9088395833969116},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.855232834815979},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.6592686772346497},{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.6095309257507324},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.6029614806175232},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.5674272775650024},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.5134838223457336},{"id":"https://openalex.org/C21821499","wikidata":"https://www.wikidata.org/wiki/Q1807064","display_name":"Lattice Boltzmann methods","level":2,"score":0.5067158341407776},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.46135497093200684},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.40969976782798767},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.23390674591064453},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.08975014090538025},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1155/2017/1205892","is_oa":true,"landing_page_url":"https://doi.org/10.1155/2017/1205892","pdf_url":"http://downloads.hindawi.com/journals/sp/2017/1205892.pdf","source":{"id":"https://openalex.org/S166774750","display_name":"Scientific Programming","issn_l":"1058-9244","issn":["1058-9244","1875-919X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319869","host_organization_name":"Hindawi Publishing Corporation","host_organization_lineage":["https://openalex.org/P4310319869"],"host_organization_lineage_names":["Hindawi Publishing Corporation"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Scientific Programming","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:db54a8f5a4d0459f831c40620f354a8f","is_oa":true,"landing_page_url":"https://doaj.org/article/db54a8f5a4d0459f831c40620f354a8f","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Scientific Programming, Vol 2017 (2017)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1155/2017/1205892","is_oa":true,"landing_page_url":"https://doi.org/10.1155/2017/1205892","pdf_url":"http://downloads.hindawi.com/journals/sp/2017/1205892.pdf","source":{"id":"https://openalex.org/S166774750","display_name":"Scientific Programming","issn_l":"1058-9244","issn":["1058-9244","1875-919X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319869","host_organization_name":"Hindawi Publishing Corporation","host_organization_lineage":["https://openalex.org/P4310319869"],"host_organization_lineage_names":["Hindawi Publishing Corporation"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Scientific Programming","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","score":0.5199999809265137,"display_name":"Affordable and clean energy"}],"awards":[{"id":"https://openalex.org/G3034753964","display_name":null,"funder_award_id":"grant","funder_id":"https://openalex.org/F4320320671","funder_display_name":"National Research Foundation"},{"id":"https://openalex.org/G342704958","display_name":null,"funder_award_id":"funded","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G3942197003","display_name":null,"funder_award_id":"20154030200770","funder_id":"https://openalex.org/F4320322349","funder_display_name":"Ministry of Education, Science and Technology"},{"id":"https://openalex.org/G4079345549","display_name":null,"funder_award_id":"2015M3C4A7065662","funder_id":"https://openalex.org/F4320320671","funder_display_name":"National Research Foundation"},{"id":"https://openalex.org/G6022346786","display_name":null,"funder_award_id":"NRF-2015M3C4A7065662","funder_id":"https://openalex.org/F4320322349","funder_display_name":"Ministry of Education, Science and Technology"},{"id":"https://openalex.org/G6421689163","display_name":null,"funder_award_id":"NRF-2015M3C4A7065662","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G6814303536","display_name":null,"funder_award_id":"2015M3C4A7065662","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G7121727950","display_name":null,"funder_award_id":"KETEP)","funder_id":"https://openalex.org/F4320335199","funder_display_name":"Korea Institute of Energy Technology Evaluation and Planning"},{"id":"https://openalex.org/G8052823794","display_name":null,"funder_award_id":"20154030200770","funder_id":"https://openalex.org/F4320335199","funder_display_name":"Korea Institute of Energy Technology Evaluation and Planning"},{"id":"https://openalex.org/G8952370644","display_name":null,"funder_award_id":"NRF-2015","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G982292920","display_name":null,"funder_award_id":"NRF-20","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"}],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"},{"id":"https://openalex.org/F4320322349","display_name":"Ministry of Education, Science and Technology","ror":"https://ror.org/01p262204"},{"id":"https://openalex.org/F4320335199","display_name":"Korea Institute of Energy Technology Evaluation and Planning","ror":"https://ror.org/02zq38y32"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2548529098.pdf","grobid_xml":"https://content.openalex.org/works/W2548529098.grobid-xml"},"referenced_works_count":15,"referenced_works":["https://openalex.org/W1622427330","https://openalex.org/W1971876223","https://openalex.org/W1982467891","https://openalex.org/W1996820070","https://openalex.org/W2036853599","https://openalex.org/W2043616378","https://openalex.org/W2059088502","https://openalex.org/W2073875590","https://openalex.org/W2074573067","https://openalex.org/W2077575837","https://openalex.org/W2108238461","https://openalex.org/W2113754927","https://openalex.org/W2149788502","https://openalex.org/W2155609373","https://openalex.org/W2276173551"],"related_works":["https://openalex.org/W4399354997","https://openalex.org/W3062287","https://openalex.org/W2380390332","https://openalex.org/W2742145873","https://openalex.org/W2023572661","https://openalex.org/W4245975140","https://openalex.org/W2532592438","https://openalex.org/W1977763331","https://openalex.org/W2062253548","https://openalex.org/W4225414539"],"abstract_inverted_index":{"Lattice":[0,180],"Boltzmann":[1],"Method":[2],"(LBM)":[3],"is":[4,20,34],"a":[5,21,25,29,56,78,117],"powerful":[6],"numerical":[7],"simulation":[8],"method":[9],"of":[10,58,74,81,100,113],"the":[11,44,47,51,62,66,70,75,87,92,97,103,114,121,125,131,135,139,147,151,158,165],"fluid":[12],"flow.":[13],"With":[14],"its":[15],"data":[16,36,45,140],"parallel":[17,26],"nature,":[18],"it":[19],"promising":[22],"candidate":[23],"for":[24,150],"implementation":[27],"on":[28,61,102,116,164],"GPU.":[30,104],"The":[31],"LBM,":[32],"however,":[33],"heavily":[35],"intensive":[37],"and":[38],"memory":[39,127],"bound.":[40],"In":[41,105],"particular,":[42],"moving":[43],"to":[46,96,156],"adjacent":[48],"cells":[49],"in":[50,154],"streaming":[52],"computation":[53,72],"phase":[54],"incurs":[55],"lot":[57],"uncoalesced":[59,126],"accesses":[60,128],"GPU":[63,118,169],"which":[64,85],"affects":[65],"overall":[67],"performance.":[68],"Furthermore,":[69,143],"main":[71],"kernels":[73,153],"LBM":[76,115,152],"use":[77],"large":[79],"number":[80,99],"registers":[82,101],"per":[83],"thread":[84,88,160],"limits":[86],"parallelism":[89],"available":[90],"at":[91],"run":[93],"time":[94],"due":[95],"fixed":[98],"this":[106],"paper,":[107],"we":[108,144],"develop":[109],"high":[110],"performance":[111],"parallelization":[112],"by":[119],"minimizing":[120],"overheads":[122],"associated":[123],"with":[124,138],"while":[129],"improving":[130],"cache":[132],"locality":[133],"using":[134],"tiling":[136],"optimization":[137],"layout":[141],"change.":[142],"aggressively":[145],"reduce":[146],"register":[148],"uses":[149],"order":[155],"increase":[157],"run-time":[159],"parallelism.":[161],"Experimental":[162],"results":[163],"Nvidia":[166],"Tesla":[167],"K20":[168],"show":[170],"that":[171],"our":[172],"approach":[173],"delivers":[174],"impressive":[175],"throughput":[176],"performance:":[177],"1210.63":[178],"Million":[179],"Updates":[181],"Per":[182],"Second":[183],"(MLUPS).":[184]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}
