{"id":"https://openalex.org/W7118083184","doi":"https://doi.org/10.1002/cpe.70518","title":"A Python/Fortran Implementation of the Lattice\u2010Boltzmann Kernel on Multiple GPU Using the OpenACC Framework","display_name":"A Python/Fortran Implementation of the Lattice\u2010Boltzmann Kernel on Multiple GPU Using the OpenACC Framework","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7118083184","doi":"https://doi.org/10.1002/cpe.70518"},"language":"en","primary_location":{"id":"doi:10.1002/cpe.70518","is_oa":true,"landing_page_url":"https://doi.org/10.1002/cpe.70518","pdf_url":null,"source":{"id":"https://openalex.org/S11065456","display_name":"Concurrency and Computation Practice and Experience","issn_l":"1532-0626","issn":["1532-0626","1532-0634"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Concurrency and Computation: Practice and Experience","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1002/cpe.70518","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5121841622","display_name":"Carlos Junqueira\u2010Junior","orcid":null},"institutions":[{"id":"https://openalex.org/I190861549","display_name":"Arts et M\u00e9tiers","ror":"https://ror.org/018pp1107","country_code":"FR","type":"education","lineage":["https://openalex.org/I190752583","https://openalex.org/I190861549","https://openalex.org/I4210134562"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Carlos Junqueira\u2010Junior","raw_affiliation_strings":["Laboratoire DynFluid Ecole Nationale Sup\u00e9rieur d'Arts et M\u00e9tiers  Paris France"],"raw_orcid":"https://orcid.org/0000-0002-4116-3012","affiliations":[{"raw_affiliation_string":"Laboratoire DynFluid Ecole Nationale Sup\u00e9rieur d'Arts et M\u00e9tiers  Paris France","institution_ids":["https://openalex.org/I190861549"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121855452","display_name":"Erwan Zamora Medina","orcid":null},"institutions":[{"id":"https://openalex.org/I124158823","display_name":"Conservatoire National des Arts et M\u00e9tiers","ror":"https://ror.org/0175hh227","country_code":"FR","type":"education","lineage":["https://openalex.org/I124158823","https://openalex.org/I4210134562"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Erwan Zamora Medina","raw_affiliation_strings":["Laboratoire DynFluid Conservatoire National des Arts et M\u00e9tiers  Paris France"],"raw_orcid":"https://orcid.org/0009-0009-2197-609X","affiliations":[{"raw_affiliation_string":"Laboratoire DynFluid Conservatoire National des Arts et M\u00e9tiers  Paris France","institution_ids":["https://openalex.org/I124158823"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121881402","display_name":"Noureddine Taibi","orcid":null},"institutions":[{"id":"https://openalex.org/I124158823","display_name":"Conservatoire National des Arts et M\u00e9tiers","ror":"https://ror.org/0175hh227","country_code":"FR","type":"education","lineage":["https://openalex.org/I124158823","https://openalex.org/I4210134562"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Noureddine Taibi","raw_affiliation_strings":["Laboratoire DynFluid Conservatoire National des Arts et M\u00e9tiers  Paris France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Laboratoire DynFluid Conservatoire National des Arts et M\u00e9tiers  Paris France","institution_ids":["https://openalex.org/I124158823"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032612132","display_name":"Simon Mari\u00e9","orcid":"https://orcid.org/0000-0002-4965-9987"},"institutions":[{"id":"https://openalex.org/I124158823","display_name":"Conservatoire National des Arts et M\u00e9tiers","ror":"https://ror.org/0175hh227","country_code":"FR","type":"education","lineage":["https://openalex.org/I124158823","https://openalex.org/I4210134562"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Simon Mari\u00e9","raw_affiliation_strings":["Laboratoire DynFluid Conservatoire National des Arts et M\u00e9tiers  Paris France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Laboratoire DynFluid Conservatoire National des Arts et M\u00e9tiers  Paris France","institution_ids":["https://openalex.org/I124158823"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5121841622"],"corresponding_institution_ids":["https://openalex.org/I190861549"],"apc_list":{"value":4740,"currency":"USD","value_usd":4740},"apc_paid":{"value":4740,"currency":"USD","value_usd":4740},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.03538398,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"38","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11751","display_name":"Lattice Boltzmann Simulation Studies","score":0.963100016117096,"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":0.963100016117096,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.014700000174343586,"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"}},{"id":"https://openalex.org/T10339","display_name":"Advanced Numerical Methods in Computational Mathematics","score":0.0032999999821186066,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/porting","display_name":"Porting","score":0.9007999897003174},{"id":"https://openalex.org/keywords/software-portability","display_name":"Software portability","score":0.8021000027656555},{"id":"https://openalex.org/keywords/solver","display_name":"Solver","score":0.663100004196167},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.603600025177002},{"id":"https://openalex.org/keywords/fortran","display_name":"Fortran","score":0.5997999906539917},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5716000199317932},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5548999905586243},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.4853000044822693},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4138999879360199}],"concepts":[{"id":"https://openalex.org/C106251023","wikidata":"https://www.wikidata.org/wiki/Q851989","display_name":"Porting","level":3,"score":0.9007999897003174},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.89410001039505},{"id":"https://openalex.org/C63000827","wikidata":"https://www.wikidata.org/wiki/Q3080428","display_name":"Software portability","level":2,"score":0.8021000027656555},{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.663100004196167},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6614999771118164},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.603600025177002},{"id":"https://openalex.org/C2778241615","wikidata":"https://www.wikidata.org/wiki/Q83303","display_name":"Fortran","level":2,"score":0.5997999906539917},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5716000199317932},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5548999905586243},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.4853000044822693},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.4771000146865845},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4138999879360199},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.4088999927043915},{"id":"https://openalex.org/C172430144","wikidata":"https://www.wikidata.org/wiki/Q17111997","display_name":"Symmetric multiprocessor system","level":2,"score":0.4081999957561493},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.4081000089645386},{"id":"https://openalex.org/C139352143","wikidata":"https://www.wikidata.org/wiki/Q82571","display_name":"Linear algebra","level":2,"score":0.31529998779296875},{"id":"https://openalex.org/C34165917","wikidata":"https://www.wikidata.org/wiki/Q188267","display_name":"Programming paradigm","level":2,"score":0.31209999322891235},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.3095000088214874},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.30660000443458557},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2937000095844269},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.2856999933719635},{"id":"https://openalex.org/C154690210","wikidata":"https://www.wikidata.org/wiki/Q1668499","display_name":"Rewriting","level":2,"score":0.2791999876499176},{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.27649998664855957},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.27480000257492065},{"id":"https://openalex.org/C168065819","wikidata":"https://www.wikidata.org/wiki/Q845566","display_name":"Debugging","level":2,"score":0.2614000141620636},{"id":"https://openalex.org/C190475519","wikidata":"https://www.wikidata.org/wiki/Q544384","display_name":"Massively parallel","level":2,"score":0.25279998779296875},{"id":"https://openalex.org/C76518257","wikidata":"https://www.wikidata.org/wiki/Q271680","display_name":"Software framework","level":5,"score":0.25040000677108765}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1002/cpe.70518","is_oa":true,"landing_page_url":"https://doi.org/10.1002/cpe.70518","pdf_url":null,"source":{"id":"https://openalex.org/S11065456","display_name":"Concurrency and Computation Practice and Experience","issn_l":"1532-0626","issn":["1532-0626","1532-0634"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Concurrency and Computation: Practice and Experience","raw_type":"journal-article"},{"id":"pmh:oai:HAL:hal-05448760v1","is_oa":true,"landing_page_url":"https://hal.science/hal-05448760","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Concurrency and Computation: Practice and Experience, 2026, 38 (1), ⟨10.1002/cpe.70518⟩","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1002/cpe.70518","is_oa":true,"landing_page_url":"https://doi.org/10.1002/cpe.70518","pdf_url":null,"source":{"id":"https://openalex.org/S11065456","display_name":"Concurrency and Computation Practice and Experience","issn_l":"1532-0626","issn":["1532-0626","1532-0634"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Concurrency and Computation: Practice and Experience","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3481504833","display_name":"Jumeaux d'Enseignement Num\u00e9riques, Immersifs et Interactifs","funder_award_id":"ANR-21-DMES-0006","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"},{"id":"https://openalex.org/G4193082115","display_name":null,"funder_award_id":"A0152A12067","funder_id":"https://openalex.org/F4320326256","funder_display_name":"Grand \u00c9quipement National De Calcul Intensif"},{"id":"https://openalex.org/G4286792273","display_name":null,"funder_award_id":"A0172A10636","funder_id":"https://openalex.org/F4320326256","funder_display_name":"Grand \u00c9quipement National De Calcul Intensif"},{"id":"https://openalex.org/G627893101","display_name":null,"funder_award_id":"A0152A10636","funder_id":"https://openalex.org/F4320326256","funder_display_name":"Grand \u00c9quipement National De Calcul Intensif"},{"id":"https://openalex.org/G8527958737","display_name":null,"funder_award_id":"A0172A12067","funder_id":"https://openalex.org/F4320326256","funder_display_name":"Grand \u00c9quipement National De Calcul Intensif"}],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"},{"id":"https://openalex.org/F4320326256","display_name":"Grand \u00c9quipement National De Calcul Intensif","ror":"https://ror.org/0010d1q40"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":71,"referenced_works":["https://openalex.org/W165267031","https://openalex.org/W820422164","https://openalex.org/W1595275604","https://openalex.org/W1767709174","https://openalex.org/W1908859542","https://openalex.org/W1963590674","https://openalex.org/W1971876223","https://openalex.org/W1972030224","https://openalex.org/W1976346389","https://openalex.org/W1979176272","https://openalex.org/W1983951810","https://openalex.org/W1984222112","https://openalex.org/W1992773065","https://openalex.org/W1994362549","https://openalex.org/W2002555321","https://openalex.org/W2022825036","https://openalex.org/W2026136326","https://openalex.org/W2029474379","https://openalex.org/W2030606751","https://openalex.org/W2032464697","https://openalex.org/W2053518117","https://openalex.org/W2054610290","https://openalex.org/W2059919683","https://openalex.org/W2062364940","https://openalex.org/W2066060292","https://openalex.org/W2067758524","https://openalex.org/W2074129693","https://openalex.org/W2082006552","https://openalex.org/W2083275413","https://openalex.org/W2083368349","https://openalex.org/W2087497493","https://openalex.org/W2092687851","https://openalex.org/W2095283463","https://openalex.org/W2113731998","https://openalex.org/W2114894811","https://openalex.org/W2126642381","https://openalex.org/W2132142914","https://openalex.org/W2151276994","https://openalex.org/W2154022181","https://openalex.org/W2167681899","https://openalex.org/W2318842505","https://openalex.org/W2580427100","https://openalex.org/W2607442078","https://openalex.org/W2635379961","https://openalex.org/W2899184388","https://openalex.org/W2908412298","https://openalex.org/W2913407901","https://openalex.org/W2943712139","https://openalex.org/W2960393003","https://openalex.org/W2970470336","https://openalex.org/W2979537058","https://openalex.org/W3011273384","https://openalex.org/W3019043644","https://openalex.org/W3026365983","https://openalex.org/W3036450597","https://openalex.org/W3039037225","https://openalex.org/W3089785124","https://openalex.org/W3122998669","https://openalex.org/W3155036733","https://openalex.org/W3156463894","https://openalex.org/W3164560424","https://openalex.org/W3204468590","https://openalex.org/W3208752547","https://openalex.org/W4221061044","https://openalex.org/W4309341372","https://openalex.org/W4312247616","https://openalex.org/W4319444034","https://openalex.org/W4360943394","https://openalex.org/W4388581272","https://openalex.org/W4392019560","https://openalex.org/W4406233735"],"related_works":[],"abstract_inverted_index":{"ABSTRACT":[0],"The":[1,53,92,148,174,193],"increasing":[2],"availability":[3],"of":[4,24,50,63,94,141,159,199],"GPU":[5,44,155,201],"accelerated":[6],"architectures":[7],"for":[8,14,76,114],"high\u2010performance":[9],"computing":[10],"presents":[11,56],"new":[12],"opportunities":[13],"scientific":[15],"software":[16],"but":[17],"also":[18],"challenges":[19],"due":[20],"to":[21,28,42,82,88,157],"the":[22,89,95,108,138,153,182,187,196,200],"complexity":[23],"porting":[25],"legacy":[26],"codes":[27],"accelerator":[29],"platforms.":[30],"Directive\u2010based":[31],"programming":[32],"models":[33],"such":[34],"as":[35],"OpenACC":[36,85],"offer":[37],"a":[38,57,64,190],"minimally":[39],"intrusive":[40],"pathway":[41],"exploit":[43],"acceleration":[45],"without":[46],"requiring":[47],"extensive":[48,128],"rewriting":[49],"existing":[51],"codes.":[52],"current":[54],"work":[55],"comprehensive":[58],"performance":[59,93,151],"and":[60,74,103,116,127,130,162,166,186,207],"portability":[61],"study":[62],"LatticeBoltzmann":[65],"Method":[66],"solver":[67,96,149],"(PyLB)":[68],"originally":[69],"written":[70],"in":[71,118,123],"Python,":[72],"Mpi4Py,":[73],"Fortran":[75,90],"CPU":[77,160],"architectures,":[78],"which":[79],"is":[80,97,176],"ported":[81],"GPUs":[83,105],"using":[84,178],"directives":[86],"applied":[87],"routines.":[91],"evaluated":[98],"on":[99,107,152],"NVIDIA":[100],"V100,":[101],"A100,":[102],"H100":[104,154],"available":[106],"Jean":[109],"Zay":[110],"supercomputer":[111],"from":[112],"Institute":[113],"Development":[115],"Resources":[117],"Intensive":[119],"Scientific":[120],"Computing":[121],"(IDRIS)":[122],"France.":[124],"Roofline":[125],"analysis":[126],"strong":[129,164],"weak":[131],"scalability":[132],"tests":[133],"are":[134],"conducted,":[135],"showing":[136],"that":[137],"GPU\u2010enabled":[139],"version":[140],"PyLB":[142],"scales":[143],"efficiently":[144],"across":[145],"multiple":[146],"GPUs.":[147],"achieves":[150],"equivalent":[156],"thousands":[158],"cores":[161],"shows":[163],"energy":[165],"carbon":[167],"efficiency":[168],"advantages":[169],"over":[170,189],"traditional":[171],"CPU\u2010based":[172],"simulations.":[173],"implementation":[175],"validated":[177],"classical":[179],"benchmarks,":[180],"including":[181],"decaying":[183],"Taylor\u2010Green":[184],"vortex":[185],"flow":[188],"3\u2010D":[191],"sphere.":[192],"results":[194],"confirm":[195],"physical":[197],"accuracy":[198],"port":[202],"while":[203],"highlighting":[204],"its":[205],"computational":[206],"environmental":[208],"advantages.":[209]},"counts_by_year":[],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2026-01-03T00:00:00"}