{"id":"https://openalex.org/W4298094978","doi":"https://doi.org/10.1145/3546000.3546014","title":"Parallel Performance and Optimization of the Lattice Boltzmann Method Software Palabos Using CUDA","display_name":"Parallel Performance and Optimization of the Lattice Boltzmann Method Software Palabos Using CUDA","publication_year":2022,"publication_date":"2022-06-23","ids":{"openalex":"https://openalex.org/W4298094978","doi":"https://doi.org/10.1145/3546000.3546014"},"language":"en","primary_location":{"id":"doi:10.1145/3546000.3546014","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3546000.3546014","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th International Conference on High Performance Compilation, Computing and Communications","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/A5032094982","display_name":"Bin Huang","orcid":"https://orcid.org/0000-0002-5503-9020"},"institutions":[{"id":"https://openalex.org/I4210142748","display_name":"Shandong Academy of Sciences","ror":"https://ror.org/04y8d6y55","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I152269853","display_name":"Qilu University of Technology","ror":"https://ror.org/04hyzq608","country_code":"CN","type":"education","lineage":["https://openalex.org/I152269853"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Bin Huang","raw_affiliation_strings":["Qilu University of Technology (Shandong Academy of Sciences), Shandong Computer Science Center (National Supercomputing Center in Jinan), China"],"affiliations":[{"raw_affiliation_string":"Qilu University of Technology (Shandong Academy of Sciences), Shandong Computer Science Center (National Supercomputing Center in Jinan), China","institution_ids":["https://openalex.org/I152269853","https://openalex.org/I4210142748"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100688026","display_name":"Anjun Liu","orcid":"https://orcid.org/0000-0002-6290-7201"},"institutions":[{"id":"https://openalex.org/I4210142748","display_name":"Shandong Academy of Sciences","ror":"https://ror.org/04y8d6y55","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I152269853","display_name":"Qilu University of Technology","ror":"https://ror.org/04hyzq608","country_code":"CN","type":"education","lineage":["https://openalex.org/I152269853"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Anjun Liu","raw_affiliation_strings":["Qilu University of Technology (Shandong Academy of Sciences), Shandong Computer Science Center (National Supercomputing Center in Jinan), China"],"affiliations":[{"raw_affiliation_string":"Qilu University of Technology (Shandong Academy of Sciences), Shandong Computer Science Center (National Supercomputing Center in Jinan), China","institution_ids":["https://openalex.org/I152269853","https://openalex.org/I4210142748"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113484217","display_name":"Min Tian","orcid":"https://orcid.org/0000-0002-3352-3145"},"institutions":[{"id":"https://openalex.org/I4210142748","display_name":"Shandong Academy of Sciences","ror":"https://ror.org/04y8d6y55","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I152269853","display_name":"Qilu University of Technology","ror":"https://ror.org/04hyzq608","country_code":"CN","type":"education","lineage":["https://openalex.org/I152269853"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Min Tian","raw_affiliation_strings":["Qilu University of Technology (Shandong Academy of Sciences), Shandong Computer Science Center (National Supercomputing Center in Jinan), China"],"affiliations":[{"raw_affiliation_string":"Qilu University of Technology (Shandong Academy of Sciences), Shandong Computer Science Center (National Supercomputing Center in Jinan), China","institution_ids":["https://openalex.org/I152269853","https://openalex.org/I4210142748"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026533187","display_name":"Jingshan Pan","orcid":"https://orcid.org/0009-0002-0968-0658"},"institutions":[{"id":"https://openalex.org/I4210142748","display_name":"Shandong Academy of Sciences","ror":"https://ror.org/04y8d6y55","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I152269853","display_name":"Qilu University of Technology","ror":"https://ror.org/04hyzq608","country_code":"CN","type":"education","lineage":["https://openalex.org/I152269853"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingshan Pan","raw_affiliation_strings":["Qilu University of Technology (Shandong Academy of Sciences), Shandong Computer Science Center (National Supercomputing Center in Jinan), China"],"affiliations":[{"raw_affiliation_string":"Qilu University of Technology (Shandong Academy of Sciences), Shandong Computer Science Center (National Supercomputing Center in Jinan), China","institution_ids":["https://openalex.org/I152269853","https://openalex.org/I4210142748"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100433655","display_name":"Yu Zhang","orcid":"https://orcid.org/0000-0002-9725-6330"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Zhang","raw_affiliation_strings":["School of Energy Science and Engineering, Harbin Institute of Technology, China"],"affiliations":[{"raw_affiliation_string":"School of Energy Science and Engineering, Harbin Institute of Technology, China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5032094982"],"corresponding_institution_ids":["https://openalex.org/I152269853","https://openalex.org/I4210142748"],"apc_list":null,"apc_paid":null,"fwci":0.4877,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.5646894,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"91","last_page":"98"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11751","display_name":"Lattice Boltzmann Simulation Studies","score":0.9998999834060669,"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":0.9998999834060669,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.991599977016449,"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"}},{"id":"https://openalex.org/T12163","display_name":"Aerosol Filtration and Electrostatic Precipitation","score":0.9799000024795532,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.8021741509437561},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7777484059333801},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.763687252998352},{"id":"https://openalex.org/keywords/lattice-boltzmann-methods","display_name":"Lattice Boltzmann methods","score":0.7512947916984558},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.7374584674835205},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.7079334259033203},{"id":"https://openalex.org/keywords/message-passing-interface","display_name":"Message Passing Interface","score":0.6524096727371216},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5679110884666443},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.4894086420536041},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.4610428512096405},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4594680964946747},{"id":"https://openalex.org/keywords/computational-fluid-dynamics","display_name":"Computational fluid dynamics","score":0.45550891757011414},{"id":"https://openalex.org/keywords/message-passing","display_name":"Message passing","score":0.28360581398010254},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.18252438306808472},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.13013151288032532},{"id":"https://openalex.org/keywords/mechanics","display_name":"Mechanics","score":0.12746107578277588},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10170960426330566}],"concepts":[{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.8021741509437561},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7777484059333801},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.763687252998352},{"id":"https://openalex.org/C21821499","wikidata":"https://www.wikidata.org/wiki/Q1807064","display_name":"Lattice Boltzmann methods","level":2,"score":0.7512947916984558},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.7374584674835205},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.7079334259033203},{"id":"https://openalex.org/C166782233","wikidata":"https://www.wikidata.org/wiki/Q127879","display_name":"Message Passing Interface","level":3,"score":0.6524096727371216},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5679110884666443},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.4894086420536041},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.4610428512096405},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4594680964946747},{"id":"https://openalex.org/C1633027","wikidata":"https://www.wikidata.org/wiki/Q815820","display_name":"Computational fluid dynamics","level":2,"score":0.45550891757011414},{"id":"https://openalex.org/C854659","wikidata":"https://www.wikidata.org/wiki/Q1859284","display_name":"Message passing","level":2,"score":0.28360581398010254},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.18252438306808472},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.13013151288032532},{"id":"https://openalex.org/C57879066","wikidata":"https://www.wikidata.org/wiki/Q41217","display_name":"Mechanics","level":1,"score":0.12746107578277588},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10170960426330566},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3546000.3546014","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3546000.3546014","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th International Conference on High Performance Compilation, Computing and Communications","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","score":0.7400000095367432,"display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1992361819","https://openalex.org/W2071642149","https://openalex.org/W2075250079","https://openalex.org/W2108157916","https://openalex.org/W2245853462","https://openalex.org/W2498861369","https://openalex.org/W2624351126","https://openalex.org/W2794031917","https://openalex.org/W2800002825","https://openalex.org/W2922480997","https://openalex.org/W2965351322","https://openalex.org/W2969975578","https://openalex.org/W2970650585","https://openalex.org/W2985187207","https://openalex.org/W3019043644","https://openalex.org/W3039899696","https://openalex.org/W3104389750","https://openalex.org/W3112327526"],"related_works":["https://openalex.org/W2058965144","https://openalex.org/W2164382479","https://openalex.org/W2146343568","https://openalex.org/W98480971","https://openalex.org/W2983282793","https://openalex.org/W1973046741","https://openalex.org/W4200215346","https://openalex.org/W2462471482","https://openalex.org/W2053585840","https://openalex.org/W2030707850"],"abstract_inverted_index":{"The":[0,67],"open-source":[1],"fluid":[2,42],"dynamics":[3],"software":[4],"Palabos":[5,28,56,72],"based":[6],"on":[7,57,61],"the":[8,46,53,90,108,119,122],"Lattice":[9],"Boltzmann":[10],"Method":[11],"(LBM)":[12],"has":[13,29,73],"been":[14],"widely":[15],"used":[16],"in":[17,77],"porous":[18],"media,":[19],"biological":[20],"fluids,":[21],"free":[22],"interfaces":[23],"and":[24,34,99],"other":[25],"physical":[26],"problems.":[27],"excellent":[30],"MPI":[31,79],"parallel":[32,86],"performance":[33,54,76],"can":[35,111],"complete":[36],"large":[37],"scale":[38],"computation":[39],"of":[40,49,55,92,121],"computational":[41],"dynamics.":[43],"To":[44],"realize":[45],"heterogeneous":[47],"parallelism":[48],"Palabos,":[50],"we":[51,82],"test":[52],"a":[58,62,74,84,114],"large-scale":[59],"simulation":[60],"general-purpose":[63],"cluster":[64],"at":[65],"first.":[66],"experimental":[68],"results":[69,105],"show":[70,106],"that":[71,107],"good":[75],"16000":[78],"processes.":[80],"Then,":[81],"designed":[83],"CUDA":[85],"optimization":[87],"algorithm":[88],"for":[89],"case":[91],"cavity":[93],"flow":[94],"according":[95],"to":[96],"address":[97],"mapping":[98],"shared":[100],"memory":[101],"optimization.":[102],"Numerical":[103],"experiments":[104],"speedup":[109],"ratio":[110,117],"achieve":[112],"about":[113],"1.5x":[115],"acceleration":[116],"when":[118],"number":[120],"grid":[123],"is":[124],"512\u00d7512\u00d7512.":[125]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}