{"id":"https://openalex.org/W4388581272","doi":"https://doi.org/10.1145/3624062.3624250","title":"Moment Representation of Regularized Lattice Boltzmann Methods on NVIDIA and AMD GPUs","display_name":"Moment Representation of Regularized Lattice Boltzmann Methods on NVIDIA and AMD GPUs","publication_year":2023,"publication_date":"2023-11-10","ids":{"openalex":"https://openalex.org/W4388581272","doi":"https://doi.org/10.1145/3624062.3624250"},"language":"en","primary_location":{"id":"doi:10.1145/3624062.3624250","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3624062.3624250","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the SC '23 Workshops of the International Conference on High Performance Computing, Network, Storage, and Analysis","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.osti.gov/biblio/2224172","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5083524237","display_name":"Pedro Valero\u2010Lara","orcid":"https://orcid.org/0000-0002-1479-4310"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Pedro Valero-Lara","raw_affiliation_strings":["Oak Ridge National Laboratory, United States of America"],"affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory, United States of America","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061838490","display_name":"Jeffrey S. Vetter","orcid":"https://orcid.org/0000-0002-2449-6720"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jeffrey Vetter","raw_affiliation_strings":["Oak Ridge National Laboratory, United States of America"],"affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory, United States of America","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018744978","display_name":"John Gounley","orcid":"https://orcid.org/0000-0001-8424-4982"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John Gounley","raw_affiliation_strings":["Oak Ridge National Laboratory, United States of America"],"affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory, United States of America","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056497188","display_name":"Amanda Randles","orcid":"https://orcid.org/0000-0001-6318-3885"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Amanda Randles","raw_affiliation_strings":["Duke University, United States of America"],"affiliations":[{"raw_affiliation_string":"Duke University, United States of America","institution_ids":["https://openalex.org/I170897317"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5083524237"],"corresponding_institution_ids":["https://openalex.org/I1289243028"],"apc_list":null,"apc_paid":null,"fwci":0.858,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.69023579,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1697","last_page":"1704"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11751","display_name":"Lattice Boltzmann Simulation Studies","score":1.0,"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":1.0,"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/T12163","display_name":"Aerosol Filtration and Electrostatic Precipitation","score":0.9879000186920166,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9508000016212463,"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/lattice-boltzmann-methods","display_name":"Lattice Boltzmann methods","score":0.8336976766586304},{"id":"https://openalex.org/keywords/solver","display_name":"Solver","score":0.7334609627723694},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7107638120651245},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6973726749420166},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6644920110702515},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.6501291394233704},{"id":"https://openalex.org/keywords/memory-footprint","display_name":"Memory footprint","score":0.630180299282074},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.5140222311019897},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.49157533049583435},{"id":"https://openalex.org/keywords/hpp-model","display_name":"HPP model","score":0.4191366136074066},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.19811567664146423},{"id":"https://openalex.org/keywords/mechanics","display_name":"Mechanics","score":0.10915747284889221}],"concepts":[{"id":"https://openalex.org/C21821499","wikidata":"https://www.wikidata.org/wiki/Q1807064","display_name":"Lattice Boltzmann methods","level":2,"score":0.8336976766586304},{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.7334609627723694},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7107638120651245},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6973726749420166},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6644920110702515},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.6501291394233704},{"id":"https://openalex.org/C74912251","wikidata":"https://www.wikidata.org/wiki/Q6815727","display_name":"Memory footprint","level":2,"score":0.630180299282074},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.5140222311019897},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.49157533049583435},{"id":"https://openalex.org/C67906445","wikidata":"https://www.wikidata.org/wiki/Q17027724","display_name":"HPP model","level":4,"score":0.4191366136074066},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.19811567664146423},{"id":"https://openalex.org/C57879066","wikidata":"https://www.wikidata.org/wiki/Q41217","display_name":"Mechanics","level":1,"score":0.10915747284889221},{"id":"https://openalex.org/C182748727","wikidata":"https://www.wikidata.org/wiki/Q178932","display_name":"Reynolds number","level":3,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C196558001","wikidata":"https://www.wikidata.org/wiki/Q190132","display_name":"Turbulence","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3624062.3624250","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3624062.3624250","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the SC '23 Workshops of the International Conference on High Performance Computing, Network, Storage, and Analysis","raw_type":"proceedings-article"},{"id":"pmh:oai:osti.gov:2224172","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/2224172","pdf_url":null,"source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:osti.gov:2224172","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/2224172","pdf_url":null,"source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},"sustainable_development_goals":[{"score":0.8399999737739563,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W569300909","https://openalex.org/W1216276171","https://openalex.org/W1971876223","https://openalex.org/W1992773065","https://openalex.org/W1999559080","https://openalex.org/W2013976274","https://openalex.org/W2083368349","https://openalex.org/W2092687851","https://openalex.org/W2136559004","https://openalex.org/W2241883738","https://openalex.org/W2508010902","https://openalex.org/W2508453970","https://openalex.org/W2554658057","https://openalex.org/W2986136620","https://openalex.org/W3005377086","https://openalex.org/W3134030220","https://openalex.org/W3158607448","https://openalex.org/W3195830194","https://openalex.org/W4320169361","https://openalex.org/W4320723327"],"related_works":["https://openalex.org/W2411948770","https://openalex.org/W2091687378","https://openalex.org/W2026659976","https://openalex.org/W2083059313","https://openalex.org/W155120597","https://openalex.org/W2062900651","https://openalex.org/W2002628205","https://openalex.org/W2289107462","https://openalex.org/W1815842106","https://openalex.org/W2374711637"],"abstract_inverted_index":{"The":[0],"lattice":[1,53,71],"Boltzmann":[2,54,72],"method":[3,25],"is":[4,26],"a":[5,18,34],"highly":[6],"scalable":[7],"Navier-Stokes":[8],"solver":[9],"that":[10],"has":[11,33],"been":[12],"applied":[13],"to":[14,61,82],"flow":[15],"problems":[16],"in":[17,86],"wide":[19],"array":[20],"of":[21,49,65],"domains.":[22],"However,":[23],"the":[24,77],"bandwidth-bound":[27],"on":[28,97],"modern":[29],"GPU":[30,47,101],"accelerators":[31],"and":[32,45,84,88,99],"large":[35],"memory":[36,78],"footprint.":[37],"In":[38],"this":[39],"paper,":[40],"we":[41],"present":[42],"new":[43,93],"2D":[44,87],"3D":[46,89],"implementations":[48,73],"two":[50],"different":[51],"regularized":[52],"methods,":[55],"which":[56],"are":[57,95],"not":[58],"only":[59],"able":[60],"achieve":[62],"an":[63],"acceleration":[64],"\u223c":[66],"1.4":[67],"\u00d7":[68],"w.r.t.":[69],"reference":[70],"but":[74],"also":[75],"reduce":[76],"requirements":[79],"by":[80],"up":[81],"35%":[83],"47%":[85],"simulations":[90],"respectively.":[91],"These":[92],"approaches":[94],"evaluated":[96],"NVIDIA":[98],"AMD":[100],"architectures.":[102]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}