{"id":"https://openalex.org/W3089221400","doi":"https://doi.org/10.1155/2020/8862123","title":"Hybrid MPI and CUDA Parallelization for CFD Applications on Multi-GPU HPC Clusters","display_name":"Hybrid MPI and CUDA Parallelization for CFD Applications on Multi-GPU HPC Clusters","publication_year":2020,"publication_date":"2020-09-25","ids":{"openalex":"https://openalex.org/W3089221400","doi":"https://doi.org/10.1155/2020/8862123","mag":"3089221400"},"language":"en","primary_location":{"id":"doi:10.1155/2020/8862123","is_oa":true,"landing_page_url":"https://doi.org/10.1155/2020/8862123","pdf_url":"https://downloads.hindawi.com/journals/sp/2020/8862123.pdf","source":{"id":"https://openalex.org/S166774750","display_name":"Scientific Programming","issn_l":"1058-9244","issn":["1058-9244","1875-919X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319869","host_organization_name":"Hindawi Publishing Corporation","host_organization_lineage":["https://openalex.org/P4310319869"],"host_organization_lineage_names":["Hindawi Publishing Corporation"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Scientific Programming","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://downloads.hindawi.com/journals/sp/2020/8862123.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047447860","display_name":"Jianqi Lai","orcid":"https://orcid.org/0000-0003-3622-6856"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jianqi Lai","raw_affiliation_strings":["College of Aerospace Science and Engineering, National University of Defense Technology, Changsha 410073, China"],"affiliations":[{"raw_affiliation_string":"College of Aerospace Science and Engineering, National University of Defense Technology, Changsha 410073, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006570796","display_name":"Hang Yu","orcid":"https://orcid.org/0000-0001-9004-6608"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hang Yu","raw_affiliation_strings":["College of Aerospace Science and Engineering, National University of Defense Technology, Changsha 410073, China"],"affiliations":[{"raw_affiliation_string":"College of Aerospace Science and Engineering, National University of Defense Technology, Changsha 410073, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073577777","display_name":"Zhengyu Tian","orcid":"https://orcid.org/0000-0003-3870-0670"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengyu Tian","raw_affiliation_strings":["College of Aerospace Science and Engineering, National University of Defense Technology, Changsha 410073, China"],"affiliations":[{"raw_affiliation_string":"College of Aerospace Science and Engineering, National University of Defense Technology, Changsha 410073, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100664742","display_name":"Hua Li","orcid":"https://orcid.org/0000-0001-7349-4628"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hua Li","raw_affiliation_strings":["College of Aerospace Science and Engineering, National University of Defense Technology, Changsha 410073, China"],"affiliations":[{"raw_affiliation_string":"College of Aerospace Science and Engineering, National University of Defense Technology, Changsha 410073, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5047447860"],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":{"value":1800,"currency":"USD","value_usd":1800},"apc_paid":{"value":1800,"currency":"USD","value_usd":1800},"fwci":3.5932,"has_fulltext":true,"cited_by_count":39,"citation_normalized_percentile":{"value":0.93926974,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"2020","issue":null,"first_page":"1","last_page":"15"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10173","display_name":"Computational Fluid Dynamics and Aerodynamics","score":0.9977999925613403,"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/T10173","display_name":"Computational Fluid Dynamics and Aerodynamics","score":0.9977999925613403,"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/T11751","display_name":"Lattice Boltzmann Simulation Studies","score":0.9965999722480774,"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":0.9934999942779541,"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":0.8582999110221863},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.8464198112487793},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7676243782043457},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.6307460069656372},{"id":"https://openalex.org/keywords/gpu-cluster","display_name":"GPU cluster","score":0.610802173614502},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.5206498503684998},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.49076446890830994},{"id":"https://openalex.org/keywords/computational-fluid-dynamics","display_name":"Computational fluid dynamics","score":0.4550415873527527},{"id":"https://openalex.org/keywords/graphics-processing-unit","display_name":"Graphics processing unit","score":0.44227397441864014},{"id":"https://openalex.org/keywords/discretization","display_name":"Discretization","score":0.42858627438545227},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.42471814155578613},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.4175720512866974},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4104290306568146},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.3254619240760803},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.12833157181739807},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.06709235906600952}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8582999110221863},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.8464198112487793},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7676243782043457},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.6307460069656372},{"id":"https://openalex.org/C2781335571","wikidata":"https://www.wikidata.org/wiki/Q2633544","display_name":"GPU cluster","level":3,"score":0.610802173614502},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.5206498503684998},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.49076446890830994},{"id":"https://openalex.org/C1633027","wikidata":"https://www.wikidata.org/wiki/Q815820","display_name":"Computational fluid dynamics","level":2,"score":0.4550415873527527},{"id":"https://openalex.org/C2779851693","wikidata":"https://www.wikidata.org/wiki/Q183484","display_name":"Graphics processing unit","level":2,"score":0.44227397441864014},{"id":"https://openalex.org/C73000952","wikidata":"https://www.wikidata.org/wiki/Q17007827","display_name":"Discretization","level":2,"score":0.42858627438545227},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.42471814155578613},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.4175720512866974},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4104290306568146},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.3254619240760803},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.12833157181739807},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.06709235906600952},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C57879066","wikidata":"https://www.wikidata.org/wiki/Q41217","display_name":"Mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1155/2020/8862123","is_oa":true,"landing_page_url":"https://doi.org/10.1155/2020/8862123","pdf_url":"https://downloads.hindawi.com/journals/sp/2020/8862123.pdf","source":{"id":"https://openalex.org/S166774750","display_name":"Scientific Programming","issn_l":"1058-9244","issn":["1058-9244","1875-919X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319869","host_organization_name":"Hindawi Publishing Corporation","host_organization_lineage":["https://openalex.org/P4310319869"],"host_organization_lineage_names":["Hindawi Publishing Corporation"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Scientific Programming","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:cbe00734b70642abb4fcc55665ac0830","is_oa":true,"landing_page_url":"https://doaj.org/article/cbe00734b70642abb4fcc55665ac0830","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Scientific Programming, Vol 2020 (2020)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1155/2020/8862123","is_oa":true,"landing_page_url":"https://doi.org/10.1155/2020/8862123","pdf_url":"https://downloads.hindawi.com/journals/sp/2020/8862123.pdf","source":{"id":"https://openalex.org/S166774750","display_name":"Scientific Programming","issn_l":"1058-9244","issn":["1058-9244","1875-919X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319869","host_organization_name":"Hindawi Publishing Corporation","host_organization_lineage":["https://openalex.org/P4310319869"],"host_organization_lineage_names":["Hindawi Publishing Corporation"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Scientific Programming","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G116334579","display_name":null,"funder_award_id":"11472004","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","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":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3089221400.pdf","grobid_xml":"https://content.openalex.org/works/W3089221400.grobid-xml"},"referenced_works_count":41,"referenced_works":["https://openalex.org/W1908859542","https://openalex.org/W1964111484","https://openalex.org/W1967394905","https://openalex.org/W1973858832","https://openalex.org/W1974097079","https://openalex.org/W1980348099","https://openalex.org/W1985658314","https://openalex.org/W1988100749","https://openalex.org/W2000596011","https://openalex.org/W2047086434","https://openalex.org/W2059955219","https://openalex.org/W2063300091","https://openalex.org/W2073045545","https://openalex.org/W2073811696","https://openalex.org/W2079360360","https://openalex.org/W2080202186","https://openalex.org/W2128007957","https://openalex.org/W2140422614","https://openalex.org/W2195884801","https://openalex.org/W2237653161","https://openalex.org/W2513293834","https://openalex.org/W2548529098","https://openalex.org/W2565063291","https://openalex.org/W2586610618","https://openalex.org/W2592859824","https://openalex.org/W2735713884","https://openalex.org/W2781486094","https://openalex.org/W2789720569","https://openalex.org/W2795169978","https://openalex.org/W2796227511","https://openalex.org/W2802800505","https://openalex.org/W2900986793","https://openalex.org/W2901728847","https://openalex.org/W2910096450","https://openalex.org/W2922284312","https://openalex.org/W2935041335","https://openalex.org/W3000561246","https://openalex.org/W3001717137","https://openalex.org/W3010292040","https://openalex.org/W3106440809","https://openalex.org/W3122264676"],"related_works":["https://openalex.org/W1963859303","https://openalex.org/W2364044215","https://openalex.org/W2389600408","https://openalex.org/W240129890","https://openalex.org/W3048701459","https://openalex.org/W2149078538","https://openalex.org/W2056717482","https://openalex.org/W2030707850","https://openalex.org/W2393490604","https://openalex.org/W2375309128"],"abstract_inverted_index":{"Graphics":[0],"processing":[1],"units":[2],"(GPUs)":[3],"have":[4,18],"a":[5,10,34,67,153,200,206,226],"strong":[6],"floating-point":[7],"capability":[8],"and":[9,17,38,76,91,101,127,129,139,164,210,239],"high":[11],"memory":[12,140],"bandwidth":[13],"in":[14,22,56],"data":[15,135,166],"parallelism":[16],"been":[19],"widely":[20],"used":[21,32,97,144,180],"high-performance":[23],"computing":[24,36],"(HPC).":[25],"Compute":[26],"unified":[27],"device":[28],"architecture":[29],"(CUDA)":[30],"is":[31,108,132,179],"as":[33],"parallel":[35,69,192,237,241],"platform":[37],"programming":[39],"model":[40],"for":[41,78,98,134],"the":[42,46,72,92,111,122,125,130,147,174,183,190,195,211,240],"GPU":[43,126,131,160,208],"to":[44,145,157,181,235],"reduce":[45],"complexity":[47],"of":[48,71,124,205,213,228],"programming.":[49],"The":[50,85,105,118,203],"programmable":[51],"GPUs":[52],"are":[53,96,143,216],"becoming":[54],"popular":[55],"computational":[57],"fluid":[58],"dynamics":[59],"(CFD)":[60],"applications.":[61],"In":[62],"this":[63],"work,":[64],"we":[65,188],"propose":[66,152],"hybrid":[68,191],"algorithm":[70,193,242],"message":[73],"passing":[74],"interface":[75],"CUDA":[77,171],"CFD":[79,149],"applications":[80],"on":[81],"multi-GPU":[82,214,222],"HPC":[83],"clusters.":[84],"AUSM":[86],"+":[87],"UP":[88],"upwind":[89],"scheme":[90],"three-step":[93],"Runge\u2013Kutta":[94],"method":[95,156,178],"spatial":[99],"discretization":[100],"time":[102],"discretization,":[103],"respectively.":[104],"turbulent":[106,197],"solution":[107],"solved":[109],"by":[110,168],"<mml:math":[112],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[113],"id=\"M1\"><mml:mi>K</mml:mi><mml:mo>\u2212</mml:mo><mml:mi>\u03c9</mml:mi></mml:math>":[114],"SST":[115],"two-equation":[116],"model.":[117],"CPU":[119],"only":[120],"manages":[121],"execution":[123,138],"communication,":[128,163],"responsible":[133],"processing.":[136],"Parallel":[137],"access":[141],"optimizations":[142],"optimize":[146],"GPU-based":[148],"codes.":[150],"We":[151],"nonblocking":[154],"communication":[155],"fully":[158],"overlap":[159],"computing,":[161,238],"CPU_CPU":[162],"CPU_GPU":[165],"transfer":[167],"creating":[169],"two":[170],"streams.":[172],"Furthermore,":[173],"one-dimensional":[175],"domain":[176],"decomposition":[177],"balance":[182],"workload":[184],"among":[185],"GPUs.":[186],"Finally,":[187],"evaluate":[189],"with":[194,233],"compressible":[196],"flow":[198],"over":[199],"flat":[201],"plate.":[202],"performance":[204],"single":[207],"implementation":[209],"scalability":[212],"clusters":[215],"discussed.":[217],"Performance":[218],"measurements":[219],"show":[220],"that":[221],"parallelization":[223],"can":[224],"achieve":[225],"speedup":[227],"more":[229],"than":[230],"36":[231],"times":[232],"respect":[234],"CPU-based":[236],"has":[243],"good":[244],"scalability.":[245]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":10}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}