{"id":"https://openalex.org/W4389897586","doi":"https://doi.org/10.1109/tpds.2023.3343706","title":"SunwayLB: Enabling Extreme-Scale Lattice Boltzmann Method Based Computing Fluid Dynamics Simulations on Advanced Heterogeneous Supercomputers","display_name":"SunwayLB: Enabling Extreme-Scale Lattice Boltzmann Method Based Computing Fluid Dynamics Simulations on Advanced Heterogeneous Supercomputers","publication_year":2023,"publication_date":"2023-12-18","ids":{"openalex":"https://openalex.org/W4389897586","doi":"https://doi.org/10.1109/tpds.2023.3343706"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2023.3343706","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2023.3343706","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-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/A5011902413","display_name":"Zhao Liu","orcid":"https://orcid.org/0000-0002-5259-4504"},"institutions":[{"id":"https://openalex.org/I4210158984","display_name":"National Supercomputing Center in Wuxi","ror":"https://ror.org/04ypjrs34","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210158984"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhao Liu","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University, Beijing, China","National Supercomputing Center in Wuxi, Wuxi, China"],"raw_orcid":"https://orcid.org/0000-0002-5259-4504","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"National Supercomputing Center in Wuxi, Wuxi, China","institution_ids":["https://openalex.org/I4210158984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012804167","display_name":"Xuesen Chu","orcid":"https://orcid.org/0000-0002-9540-5961"},"institutions":[{"id":"https://openalex.org/I4210129465","display_name":"Wuhan Ship Development & Design Institute","ror":"https://ror.org/02mcdae06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210129465"]},{"id":"https://openalex.org/I4210154710","display_name":"Wuxi Taihu Hospital","ror":"https://ror.org/05qp6pd10","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210154710"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuesen Chu","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University, Beijing, China","Taihu Laboratory of DeepSea Technological Science, Wuxi, China","China Ship Scientific Research Center, Wuxi, China"],"raw_orcid":"https://orcid.org/0000-0002-9540-5961","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Taihu Laboratory of DeepSea Technological Science, Wuxi, China","institution_ids":["https://openalex.org/I4210154710"]},{"raw_affiliation_string":"China Ship Scientific Research Center, Wuxi, China","institution_ids":["https://openalex.org/I4210129465"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025153674","display_name":"Xiaojing Lv","orcid":"https://orcid.org/0000-0003-1557-7550"},"institutions":[{"id":"https://openalex.org/I4210129465","display_name":"Wuhan Ship Development & Design Institute","ror":"https://ror.org/02mcdae06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210129465"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaojing Lv","raw_affiliation_strings":["Department of Software Engineering and Technology, China Ship Scientific Research Center, Wuxi, China"],"raw_orcid":"https://orcid.org/0000-0003-1557-7550","affiliations":[{"raw_affiliation_string":"Department of Software Engineering and Technology, China Ship Scientific Research Center, Wuxi, China","institution_ids":["https://openalex.org/I4210129465"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049509104","display_name":"Hongsong Meng","orcid":null},"institutions":[{"id":"https://openalex.org/I4210158984","display_name":"National Supercomputing Center in Wuxi","ror":"https://ror.org/04ypjrs34","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210158984"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongsong Meng","raw_affiliation_strings":["Department of Parallel Optimization, National Supercomputing Center in Wuxi, Wuxi, China"],"raw_orcid":"https://orcid.org/0009-0007-7899-7807","affiliations":[{"raw_affiliation_string":"Department of Parallel Optimization, National Supercomputing Center in Wuxi, Wuxi, China","institution_ids":["https://openalex.org/I4210158984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015097405","display_name":"Hanyue Liu","orcid":"https://orcid.org/0009-0009-5724-2821"},"institutions":[{"id":"https://openalex.org/I4210158984","display_name":"National Supercomputing Center in Wuxi","ror":"https://ror.org/04ypjrs34","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210158984"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hanyue Liu","raw_affiliation_strings":["Department of Parallel Optimization, National Supercomputing Center in Wuxi, Wuxi, China"],"raw_orcid":"https://orcid.org/0009-0009-5724-2821","affiliations":[{"raw_affiliation_string":"Department of Parallel Optimization, National Supercomputing Center in Wuxi, Wuxi, China","institution_ids":["https://openalex.org/I4210158984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103254413","display_name":"Guanghui Zhu","orcid":"https://orcid.org/0009-0006-4901-8131"},"institutions":[{"id":"https://openalex.org/I38877650","display_name":"Zhengzhou University","ror":"https://ror.org/04ypx8c21","country_code":"CN","type":"education","lineage":["https://openalex.org/I38877650"]},{"id":"https://openalex.org/I4210110458","display_name":"Institute of Electronics","ror":"https://ror.org/01z143507","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210110458"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guanghui Zhu","raw_affiliation_strings":["Institute of Electronics and Information Technology, Zhengzhou University of Technology, Zhengzhou, China","Department of Government and Enterprise Business, Huirong Electronic Systems Engineering Company Ltd., Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0006-4901-8131","affiliations":[{"raw_affiliation_string":"Institute of Electronics and Information Technology, Zhengzhou University of Technology, Zhengzhou, China","institution_ids":["https://openalex.org/I38877650","https://openalex.org/I4210110458"]},{"raw_affiliation_string":"Department of Government and Enterprise Business, Huirong Electronic Systems Engineering Company Ltd., Shanghai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031545295","display_name":"Haohuan Fu","orcid":"https://orcid.org/0000-0002-6982-2235"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haohuan Fu","raw_affiliation_strings":["Department of Earth System Science, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-6982-2235","affiliations":[{"raw_affiliation_string":"Department of Earth System Science, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101678397","display_name":"Guangwen Yang","orcid":"https://orcid.org/0000-0002-8673-8254"},"institutions":[{"id":"https://openalex.org/I4210158984","display_name":"National Supercomputing Center in Wuxi","ror":"https://ror.org/04ypjrs34","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210158984"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangwen Yang","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University, Beijing, China","National Supercomputing Center in Wuxi, Wuxi, China"],"raw_orcid":"https://orcid.org/0000-0002-8673-8254","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"National Supercomputing Center in Wuxi, Wuxi, China","institution_ids":["https://openalex.org/I4210158984"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.6336,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.81393726,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"35","issue":"2","first_page":"324","last_page":"337"},"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":0.9739000201225281,"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":0.9664000272750854,"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/supercomputer","display_name":"Supercomputer","score":0.9418449997901917},{"id":"https://openalex.org/keywords/petascale-computing","display_name":"Petascale computing","score":0.8007854223251343},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7964093685150146},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6855480670928955},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6460542678833008},{"id":"https://openalex.org/keywords/lattice-boltzmann-methods","display_name":"Lattice Boltzmann methods","score":0.6187084317207336},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.5836400389671326},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.5561585426330566},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.5147833824157715},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.13378190994262695},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08220246434211731}],"concepts":[{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.9418449997901917},{"id":"https://openalex.org/C185410017","wikidata":"https://www.wikidata.org/wiki/Q7171778","display_name":"Petascale computing","level":3,"score":0.8007854223251343},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7964093685150146},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6855480670928955},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6460542678833008},{"id":"https://openalex.org/C21821499","wikidata":"https://www.wikidata.org/wiki/Q1807064","display_name":"Lattice Boltzmann methods","level":2,"score":0.6187084317207336},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.5836400389671326},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.5561585426330566},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.5147833824157715},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.13378190994262695},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08220246434211731},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tpds.2023.3343706","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2023.3343706","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.5099999904632568,"display_name":"Industry, innovation and infrastructure"}],"awards":[{"id":"https://openalex.org/G6690759662","display_name":null,"funder_award_id":"T2125006","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W28686159","https://openalex.org/W128889874","https://openalex.org/W1970172627","https://openalex.org/W1971876223","https://openalex.org/W1982412663","https://openalex.org/W1992773065","https://openalex.org/W2001250863","https://openalex.org/W2002555321","https://openalex.org/W2023387488","https://openalex.org/W2040259398","https://openalex.org/W2054372636","https://openalex.org/W2066886134","https://openalex.org/W2069010282","https://openalex.org/W2071642149","https://openalex.org/W2075460388","https://openalex.org/W2077575837","https://openalex.org/W2082006552","https://openalex.org/W2089297419","https://openalex.org/W2099621829","https://openalex.org/W2106821446","https://openalex.org/W2108238461","https://openalex.org/W2113754927","https://openalex.org/W2168795429","https://openalex.org/W2245853462","https://openalex.org/W2291499491","https://openalex.org/W2475126267","https://openalex.org/W2554658057","https://openalex.org/W2635379961","https://openalex.org/W2728256789","https://openalex.org/W2743163708","https://openalex.org/W2767373187","https://openalex.org/W2769126660","https://openalex.org/W2808191052","https://openalex.org/W2971815557","https://openalex.org/W2987526375","https://openalex.org/W3099053820","https://openalex.org/W3104389750","https://openalex.org/W3195830194","https://openalex.org/W3208078891","https://openalex.org/W4321636692"],"related_works":["https://openalex.org/W2021702679","https://openalex.org/W3038449658","https://openalex.org/W1582746211","https://openalex.org/W3129378740","https://openalex.org/W2607572736","https://openalex.org/W2266027327","https://openalex.org/W2278366184","https://openalex.org/W1486544172","https://openalex.org/W4206324154","https://openalex.org/W1978931242"],"abstract_inverted_index":{"The":[0,255],"Lattice":[1],"Boltzmann":[2],"Method":[3],"(LBM)":[4],"is":[5,261],"a":[6,63,72,84,115,144,165,194,213,231,265],"class":[7],"of":[8,60,147,164,168,197,204,233,243,252],"Computational":[9],"Fluid":[10],"Dynamics":[11],"methods":[12],"which":[13,29],"models":[14],"the":[15,44,53,58,110,153,161,172,176,202,248],"fluid":[16,239],"as":[17,43,241],"fictive":[18],"particles.":[19],"In":[20],"this":[21],"paper,":[22],"we":[23,99,207],"report":[24],"our":[25,121,205,210,253,259],"work":[26],"on":[27,95,104,275],"SunwayLB,":[28,61],"enables":[30],"LBM":[31],"based":[32],"solutions":[33],"aiming":[34],"for":[35,83,91,236,271],"industrial":[36],"applications":[37],"using":[38,160],"advanced":[39,106],"heterogeneous":[40,276],"systems":[41],"such":[42],"Sunway":[45,108,112,119,169,174],"supercomputers.":[46],"We":[47,150,229],"propose":[48],"several":[49],"techniques":[50],"to":[51,76,101,126,212,246,263],"boost":[52],"simulation":[54,123,178],"speed":[55],"and":[56,68,88,114,143,157,193,224,250,268],"improve":[57,152],"scalability":[59],"including":[62],"customized":[64],"multi-level":[65],"domain":[66],"decomposition":[67],"data":[69],"sharing":[70],"scheme,":[71],"carefully":[73],"orchestrated":[74],"strategy":[75],"fuse":[77],"kernels":[78],"with":[79,216],"different":[80],"performance":[81,146,196,251],"constraints":[82],"more":[85],"balanced":[86],"workload,":[87],"optimization":[89,97,218],"strategies":[90],"assembly":[92],"code.":[93],"Based":[94],"these":[96],"schemes,":[98],"manage":[100],"scale":[102,238],"SunwayLB":[103],"three":[105],"supercomputers:":[107],"TaihuLight,":[109,120],"new":[111,166,173],"Supercomputer":[113],"GPU":[116,214],"cluster.":[117],"On":[118,171],"largest":[122,177],"involves":[124],"up":[125],"5.6":[127],"trillion":[128,182],"lattice":[129,183],"cells,":[130,184],"achieving":[131],"11,245":[132],"billion":[133],"cell":[134],"updates":[135],"per":[136],"second":[137],"(GLUPS),":[138],"77%":[139],"memory":[140,154,190,226],"bandwidth":[141,155,191,227],"utilization":[142,156,192],"sustained":[145,195],"4.7":[148],"PFlops.":[149,199],"further":[151],"computational":[158,234],"efficiency":[159],"unique":[162],"features":[163],"generation":[167],"supercomputer.":[170],"Supercomputer,":[175],"contains":[179],"over":[180],"4.2":[181],"resulting":[185,220],"in":[186,221],"6,583":[187],"GLUPS,":[188],"81%":[189],"2.76":[198],"To":[200],"evaluate":[201],"portability":[203],"code,":[206],"also":[208],"adapt":[209],"code":[211],"cluster":[215],"tailored":[217],"techniques,":[219],"191x":[222],"speedup":[223],"83.8%":[225],"utilization.":[228],"demonstrate":[230],"series":[232],"experiments":[235],"extreme-large":[237],"flow,":[240],"examples":[242],"real-world":[244],"applications,":[245],"check":[247],"validity":[249],"work.":[254],"results":[256],"show":[257],"that":[258],"implementation":[260],"competent":[262],"be":[264],"highly":[266],"scalable":[267],"efficient":[269],"solution":[270],"large-scale":[272],"CFD":[273],"problems":[274],"systems.":[277]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}