{"id":"https://openalex.org/W4312997788","doi":"https://doi.org/10.1145/3560442.3560443","title":"Massively parallel acceleration of unstructured DSMC computing","display_name":"Massively parallel acceleration of unstructured DSMC computing","publication_year":2022,"publication_date":"2022-07-08","ids":{"openalex":"https://openalex.org/W4312997788","doi":"https://doi.org/10.1145/3560442.3560443"},"language":"en","primary_location":{"id":"doi:10.1145/3560442.3560443","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3560442.3560443","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 6th High Performance Computing and Cluster Technologies Conference","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/A5016221844","display_name":"Jin Li","orcid":"https://orcid.org/0000-0001-5897-3364"},"institutions":[{"id":"https://openalex.org/I2802505932","display_name":"China Aerodynamics Research and Development Center","ror":"https://ror.org/00jma8s40","country_code":"CN","type":"facility","lineage":["https://openalex.org/I2802505932"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jin Li","raw_affiliation_strings":["China Aerodynamics Research and Development Center, China"],"affiliations":[{"raw_affiliation_string":"China Aerodynamics Research and Development Center, China","institution_ids":["https://openalex.org/I2802505932"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101831109","display_name":"Zheming Zhang","orcid":"https://orcid.org/0000-0002-5394-0261"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheming Zhang","raw_affiliation_strings":["University of Electronic Science and Technology of China, China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023992845","display_name":"Liang Deng","orcid":"https://orcid.org/0000-0003-1444-4588"},"institutions":[{"id":"https://openalex.org/I2802505932","display_name":"China Aerodynamics Research and Development Center","ror":"https://ror.org/00jma8s40","country_code":"CN","type":"facility","lineage":["https://openalex.org/I2802505932"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Deng","raw_affiliation_strings":["China Aerodynamics Research and Development Center, China"],"affiliations":[{"raw_affiliation_string":"China Aerodynamics Research and Development Center, China","institution_ids":["https://openalex.org/I2802505932"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058656712","display_name":"Xin Ding","orcid":"https://orcid.org/0000-0003-2429-7147"},"institutions":[{"id":"https://openalex.org/I2802505932","display_name":"China Aerodynamics Research and Development Center","ror":"https://ror.org/00jma8s40","country_code":"CN","type":"facility","lineage":["https://openalex.org/I2802505932"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Ding","raw_affiliation_strings":["China Aerodynamics Research and Development Center, China"],"affiliations":[{"raw_affiliation_string":"China Aerodynamics Research and Development Center, China","institution_ids":["https://openalex.org/I2802505932"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010869450","display_name":"Dingwu Jiang","orcid":null},"institutions":[{"id":"https://openalex.org/I2802505932","display_name":"China Aerodynamics Research and Development Center","ror":"https://ror.org/00jma8s40","country_code":"CN","type":"facility","lineage":["https://openalex.org/I2802505932"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dingwu Jiang","raw_affiliation_strings":["China Aerodynamics Research and Development Center, China"],"affiliations":[{"raw_affiliation_string":"China Aerodynamics Research and Development Center, China","institution_ids":["https://openalex.org/I2802505932"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100462633","display_name":"Pei Wang","orcid":"https://orcid.org/0000-0002-1792-220X"},"institutions":[{"id":"https://openalex.org/I2802505932","display_name":"China Aerodynamics Research and Development Center","ror":"https://ror.org/00jma8s40","country_code":"CN","type":"facility","lineage":["https://openalex.org/I2802505932"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pei Wang","raw_affiliation_strings":["China Aerodynamics Research and Development Center, China"],"affiliations":[{"raw_affiliation_string":"China Aerodynamics Research and Development Center, China","institution_ids":["https://openalex.org/I2802505932"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5016221844"],"corresponding_institution_ids":["https://openalex.org/I2802505932"],"apc_list":null,"apc_paid":null,"fwci":1.0546,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.75588883,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11012","display_name":"Gas Dynamics and Kinetic Theory","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/2604","display_name":"Applied Mathematics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11012","display_name":"Gas Dynamics and Kinetic Theory","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/2604","display_name":"Applied Mathematics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10173","display_name":"Computational Fluid Dynamics and Aerodynamics","score":0.992900013923645,"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/T10360","display_name":"Fluid Dynamics and Turbulent Flows","score":0.9830999970436096,"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/parallel-computing","display_name":"Parallel computing","score":0.8324199914932251},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8113282322883606},{"id":"https://openalex.org/keywords/message-passing-interface","display_name":"Message Passing Interface","score":0.6308583617210388},{"id":"https://openalex.org/keywords/massively-parallel","display_name":"Massively parallel","score":0.6116384267807007},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5948008894920349},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.5653718709945679},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.5456860065460205},{"id":"https://openalex.org/keywords/solver","display_name":"Solver","score":0.5290084481239319},{"id":"https://openalex.org/keywords/parallel-algorithm","display_name":"Parallel algorithm","score":0.5149312615394592},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.5070350170135498},{"id":"https://openalex.org/keywords/acceleration","display_name":"Acceleration","score":0.4832354485988617},{"id":"https://openalex.org/keywords/distributed-memory","display_name":"Distributed memory","score":0.44690296053886414},{"id":"https://openalex.org/keywords/shared-memory","display_name":"Shared memory","score":0.43243342638015747},{"id":"https://openalex.org/keywords/symmetric-multiprocessor-system","display_name":"Symmetric multiprocessor system","score":0.42611217498779297},{"id":"https://openalex.org/keywords/software-portability","display_name":"Software portability","score":0.420744389295578},{"id":"https://openalex.org/keywords/message-passing","display_name":"Message passing","score":0.2970324754714966},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.0875987708568573}],"concepts":[{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.8324199914932251},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8113282322883606},{"id":"https://openalex.org/C166782233","wikidata":"https://www.wikidata.org/wiki/Q127879","display_name":"Message Passing Interface","level":3,"score":0.6308583617210388},{"id":"https://openalex.org/C190475519","wikidata":"https://www.wikidata.org/wiki/Q544384","display_name":"Massively parallel","level":2,"score":0.6116384267807007},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5948008894920349},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.5653718709945679},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.5456860065460205},{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.5290084481239319},{"id":"https://openalex.org/C120373497","wikidata":"https://www.wikidata.org/wiki/Q1087987","display_name":"Parallel algorithm","level":2,"score":0.5149312615394592},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.5070350170135498},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.4832354485988617},{"id":"https://openalex.org/C91481028","wikidata":"https://www.wikidata.org/wiki/Q1054686","display_name":"Distributed memory","level":3,"score":0.44690296053886414},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.43243342638015747},{"id":"https://openalex.org/C172430144","wikidata":"https://www.wikidata.org/wiki/Q17111997","display_name":"Symmetric multiprocessor system","level":2,"score":0.42611217498779297},{"id":"https://openalex.org/C63000827","wikidata":"https://www.wikidata.org/wiki/Q3080428","display_name":"Software portability","level":2,"score":0.420744389295578},{"id":"https://openalex.org/C854659","wikidata":"https://www.wikidata.org/wiki/Q1859284","display_name":"Message passing","level":2,"score":0.2970324754714966},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0875987708568573},{"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/C74650414","wikidata":"https://www.wikidata.org/wiki/Q11397","display_name":"Classical mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3560442.3560443","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3560442.3560443","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 6th High Performance Computing and Cluster Technologies Conference","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.4000000059604645,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W1963831041","https://openalex.org/W2019044473","https://openalex.org/W2033847453","https://openalex.org/W2040437529","https://openalex.org/W2056056808","https://openalex.org/W2788713988","https://openalex.org/W3151941575"],"related_works":["https://openalex.org/W2026512611","https://openalex.org/W1985165680","https://openalex.org/W4245497162","https://openalex.org/W2353146130","https://openalex.org/W1990817968","https://openalex.org/W2154020360","https://openalex.org/W2498758832","https://openalex.org/W2752803751","https://openalex.org/W2080451007","https://openalex.org/W2133825528"],"abstract_inverted_index":{"The":[0],"Direct":[1],"Simulation":[2],"Monte":[3],"Carlo":[4],"(DSMC)":[5],"method":[6,23,91],"is":[7,28,49,135,149,232],"the":[8,21,60,75,108,115,125,143,146,155,168,174,179,224],"most":[9],"widely":[10],"used":[11],"technique":[12],"for":[13,38,240],"studying":[14],"complex":[15,32],"non-equilibrium":[16],"rarefied":[17],"gas":[18],"flows,":[19],"and":[20,54,65,84,92,100,121,197,219,228,235],"DSMC":[22,72],"based":[24,130],"on":[25,52,69,131,226],"unstructured":[26,71],"meshes":[27],"easy":[29],"to":[30,80,113,167,194,209],"handle":[31],"geometries,":[33],"but":[34],"has":[35,186,201,214],"higher":[36],"requirements":[37],"computing":[39,176,185,200,230,242],"resources.":[40],"In":[41,222],"this":[42],"paper,":[43],"a":[44,138],"large-scale":[45,152],"parallel":[46,96,128,147,158,171,184,199,216,241],"acceleration":[47,162,189,204,217],"study":[48],"carried":[50],"out":[51],"homogeneous":[53,76,227],"heterogeneous":[55,109,229],"computer":[56],"architectures":[57],"by":[58],"analyzing":[59],"data":[61,82,89,123],"structure,":[62],"numerical":[63],"methods":[64,104],"computational":[66],"processes":[67],"basing":[68],"an":[70,87,93,161,188,203],"solver.":[73],"For":[74,107,151],"architecture,":[77,110],"in":[78,111],"order":[79,112],"minimize":[81],"communication":[83,90],"maximize":[85],"parallelism,":[86],"efficient":[88],"MPI+OpenMP":[94,156],"hybrid":[95,127,157,183],"algorithm":[97,148],"are":[98,105],"designed,":[99],"several":[101],"performance":[102],"optimization":[103],"discussed.":[106],"alleviate":[114],"complexity":[116],"of":[117,145,164,191,206,243],"GPU":[118],"memory":[119,133],"management":[120],"improve":[122],"locality,":[124],"MPI+OpenACC":[126],"strategy":[129,159,172],"unified":[132],"technology":[134],"proposed.":[136],"Using":[137],"3D":[139],"hypersonic":[140],"plate":[141],"flow,":[142],"accuracy":[144],"verified.":[150],"test":[153],"studies,":[154],"achieves":[160],"ratio":[163,190,205],"6.18":[165],"compared":[166,234],"pure":[169],"MPI":[170],"at":[173],"8,000-core":[175],"scale.":[177],"At":[178],"same":[180],"time,":[181],"60,000-core":[182],"obtained":[187,202],"5.54":[192],"(compared":[193,208],"1024":[195],"cores),":[196],"8-GPU":[198],"32.04":[207],"CPU":[210],"single":[211],"core),":[212],"which":[213,237],"strong":[215],"capabilities":[218],"good":[220],"scalability.":[221],"addition,":[223],"portability":[225],"platforms":[231],"also":[233],"analyzed,":[236],"provides":[238],"reference":[239],"similar":[244],"application":[245],"problems.":[246]},"counts_by_year":[{"year":2024,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
