{"id":"https://openalex.org/W2923019867","doi":"https://doi.org/10.1109/empdp.2019.8671583","title":"A Dynamic Task-Based D3Q19 Lattice-Boltzmann Method for Heterogeneous Architectures","display_name":"A Dynamic Task-Based D3Q19 Lattice-Boltzmann Method for Heterogeneous Architectures","publication_year":2019,"publication_date":"2019-02-01","ids":{"openalex":"https://openalex.org/W2923019867","doi":"https://doi.org/10.1109/empdp.2019.8671583","mag":"2923019867"},"language":"en","primary_location":{"id":"doi:10.1109/empdp.2019.8671583","is_oa":false,"landing_page_url":"https://doi.org/10.1109/empdp.2019.8671583","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 27th Euromicro International Conference on Parallel, Distributed and Network-Based Processing (PDP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055527543","display_name":"Jo\u00e3o V. F. Lima","orcid":"https://orcid.org/0000-0002-2670-6963"},"institutions":[{"id":"https://openalex.org/I33501960","display_name":"Universidade Federal de Santa Maria","ror":"https://ror.org/01b78mz79","country_code":"BR","type":"education","lineage":["https://openalex.org/I33501960"]}],"countries":["BR"],"is_corresponding":true,"raw_author_name":"Joao V. F. Lima","raw_affiliation_strings":["Universidade Federal de Santa Maria, Brazil"],"affiliations":[{"raw_affiliation_string":"Universidade Federal de Santa Maria, Brazil","institution_ids":["https://openalex.org/I33501960"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006984221","display_name":"Gabriel Freytag","orcid":"https://orcid.org/0000-0001-6081-5904"},"institutions":[{"id":"https://openalex.org/I130442723","display_name":"Universidade Federal do Rio Grande do Sul","ror":"https://ror.org/041yk2d64","country_code":"BR","type":"education","lineage":["https://openalex.org/I130442723"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Gabriel Freytag","raw_affiliation_strings":["Universidade Federal do Rio Grande do Sul, Brazil"],"affiliations":[{"raw_affiliation_string":"Universidade Federal do Rio Grande do Sul, Brazil","institution_ids":["https://openalex.org/I130442723"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071466107","display_name":"Vin\u00edcius Garcia Pinto","orcid":"https://orcid.org/0000-0002-6845-9358"},"institutions":[{"id":"https://openalex.org/I130442723","display_name":"Universidade Federal do Rio Grande do Sul","ror":"https://ror.org/041yk2d64","country_code":"BR","type":"education","lineage":["https://openalex.org/I130442723"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Vinicius Garcia Pinto","raw_affiliation_strings":["Universidade Federal do Rio Grande do Sul, Brazil"],"affiliations":[{"raw_affiliation_string":"Universidade Federal do Rio Grande do Sul, Brazil","institution_ids":["https://openalex.org/I130442723"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000753723","display_name":"Cl\u00e1udio Schepke","orcid":"https://orcid.org/0000-0003-4118-8831"},"institutions":[{"id":"https://openalex.org/I72872986","display_name":"Universidade Federal do Pampa","ror":"https://ror.org/003qt4p19","country_code":"BR","type":"education","lineage":["https://openalex.org/I72872986"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Claudio Schepke","raw_affiliation_strings":["Universidade Federal do Pampa, Campus Alegrete, Brazil"],"affiliations":[{"raw_affiliation_string":"Universidade Federal do Pampa, Campus Alegrete, Brazil","institution_ids":["https://openalex.org/I72872986"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091234084","display_name":"Philippe O. A. Navaux","orcid":"https://orcid.org/0000-0002-9957-5861"},"institutions":[{"id":"https://openalex.org/I130442723","display_name":"Universidade Federal do Rio Grande do Sul","ror":"https://ror.org/041yk2d64","country_code":"BR","type":"education","lineage":["https://openalex.org/I130442723"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Philippe O. A. Navaux","raw_affiliation_strings":["Universidade Federal do Rio Grande do Sul, Brazil"],"affiliations":[{"raw_affiliation_string":"Universidade Federal do Rio Grande do Sul, Brazil","institution_ids":["https://openalex.org/I130442723"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5055527543"],"corresponding_institution_ids":["https://openalex.org/I33501960"],"apc_list":null,"apc_paid":null,"fwci":0.3783,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.56758688,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":"213","issue":null,"first_page":"108","last_page":"115"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11751","display_name":"Lattice Boltzmann Simulation Studies","score":0.9986000061035156,"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":0.9986000061035156,"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":0.9958000183105469,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9955999851226807,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/computer-science","display_name":"Computer science","score":0.8750734329223633},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7740577459335327},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.7062782645225525},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5951201319694519},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.5634467005729675},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.5538873076438904},{"id":"https://openalex.org/keywords/programming-paradigm","display_name":"Programming paradigm","score":0.5522899627685547},{"id":"https://openalex.org/keywords/symmetric-multiprocessor-system","display_name":"Symmetric multiprocessor system","score":0.5395464301109314},{"id":"https://openalex.org/keywords/lattice-boltzmann-methods","display_name":"Lattice Boltzmann methods","score":0.5174134969711304},{"id":"https://openalex.org/keywords/task-parallelism","display_name":"Task parallelism","score":0.48831459879875183},{"id":"https://openalex.org/keywords/parallel-programming-model","display_name":"Parallel programming model","score":0.4682180881500244},{"id":"https://openalex.org/keywords/data-parallelism","display_name":"Data parallelism","score":0.44283580780029297},{"id":"https://openalex.org/keywords/runtime-system","display_name":"Runtime system","score":0.42596104741096497},{"id":"https://openalex.org/keywords/parallelism","display_name":"Parallelism (grammar)","score":0.28320759534835815},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.12998411059379578}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8750734329223633},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7740577459335327},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.7062782645225525},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5951201319694519},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.5634467005729675},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.5538873076438904},{"id":"https://openalex.org/C34165917","wikidata":"https://www.wikidata.org/wiki/Q188267","display_name":"Programming paradigm","level":2,"score":0.5522899627685547},{"id":"https://openalex.org/C172430144","wikidata":"https://www.wikidata.org/wiki/Q17111997","display_name":"Symmetric multiprocessor system","level":2,"score":0.5395464301109314},{"id":"https://openalex.org/C21821499","wikidata":"https://www.wikidata.org/wiki/Q1807064","display_name":"Lattice Boltzmann methods","level":2,"score":0.5174134969711304},{"id":"https://openalex.org/C42992933","wikidata":"https://www.wikidata.org/wiki/Q691169","display_name":"Task parallelism","level":3,"score":0.48831459879875183},{"id":"https://openalex.org/C137364921","wikidata":"https://www.wikidata.org/wiki/Q27929394","display_name":"Parallel programming model","level":3,"score":0.4682180881500244},{"id":"https://openalex.org/C61483411","wikidata":"https://www.wikidata.org/wiki/Q3124522","display_name":"Data parallelism","level":3,"score":0.44283580780029297},{"id":"https://openalex.org/C2780870223","wikidata":"https://www.wikidata.org/wiki/Q1004415","display_name":"Runtime system","level":2,"score":0.42596104741096497},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.28320759534835815},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.12998411059379578},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/empdp.2019.8671583","is_oa":false,"landing_page_url":"https://doi.org/10.1109/empdp.2019.8671583","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 27th Euromicro International Conference on Parallel, Distributed and Network-Based Processing (PDP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1720285298","https://openalex.org/W1967925433","https://openalex.org/W1982068804","https://openalex.org/W1992299697","https://openalex.org/W2013121458","https://openalex.org/W2016716665","https://openalex.org/W2064744742","https://openalex.org/W2065067332","https://openalex.org/W2072725684","https://openalex.org/W2104008467","https://openalex.org/W2106821446","https://openalex.org/W2113941519","https://openalex.org/W2117242079","https://openalex.org/W2121893797","https://openalex.org/W2124480634","https://openalex.org/W2171226522","https://openalex.org/W2245396003","https://openalex.org/W2294224064","https://openalex.org/W2508453970","https://openalex.org/W2513293834","https://openalex.org/W2541796905","https://openalex.org/W2563399153","https://openalex.org/W2567328234","https://openalex.org/W2589238145","https://openalex.org/W2593784973","https://openalex.org/W2608852956","https://openalex.org/W2750442496","https://openalex.org/W3106440809","https://openalex.org/W4234740575","https://openalex.org/W4234823558","https://openalex.org/W4243461974"],"related_works":["https://openalex.org/W2142344422","https://openalex.org/W1483753031","https://openalex.org/W2073582220","https://openalex.org/W2085780778","https://openalex.org/W2103813409","https://openalex.org/W2378666660","https://openalex.org/W4253043195","https://openalex.org/W1784161403","https://openalex.org/W2139618719","https://openalex.org/W297872448"],"abstract_inverted_index":{"Nowadays":[0],"computing":[1,80],"platforms":[2,55],"expose":[3],"a":[4,23,87],"significant":[5],"number":[6],"of":[7,62,69,126],"heterogeneous":[8,54,98,113],"processing":[9],"units":[10],"such":[11,29],"as":[12],"multicore":[13],"processors":[14],"and":[15,102,108],"accelerators.":[16,57],"The":[17],"task-based":[18,67,89,120],"programming":[19,35],"model":[20,27,33],"has":[21,74],"been":[22,75],"de":[24],"facto":[25],"standard":[26],"for":[28,97],"architectures":[30],"since":[31],"its":[32],"simplifies":[34],"by":[36],"unfolding":[37],"parallelism":[38],"at":[39],"runtime":[40,95],"based":[41],"on":[42],"data-flow":[43],"dependencies":[44],"between":[45],"tasks.":[46],"Many":[47],"studies":[48],"have":[49],"proposed":[50,76],"parallel":[51,131],"strategies":[52],"over":[53,111,128],"with":[56],"However,":[58],"to":[59,77,124],"the":[60,70],"best":[61],"our":[63,106,119],"knowledge,":[64],"no":[65],"dynamic":[66,88],"strategy":[68],"Lattice-Boltzmann":[71],"Method":[72],"(LBM)":[73],"exploit":[78],"CPU+GPU":[79],"nodes.":[81],"In":[82],"this":[83],"paper,":[84],"we":[85],"present":[86],"D3Q19":[90],"LBM":[91],"implementation":[92],"using":[93],"three":[94],"systems":[96],"architectures:":[99],"OmpSs,":[100],"StarPU,":[101],"XKaapi.":[103],"We":[104],"detail":[105],"implementations":[107],"compare":[109],"performance":[110],"two":[112],"platforms.":[114],"Experimental":[115],"results":[116],"demonstrate":[117],"that":[118],"approach":[121],"attained":[122],"up":[123],"8.8":[125],"speedup":[127],"an":[129],"OpenMP":[130],"loop":[132],"version.":[133]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
