{"id":"https://openalex.org/W2314584550","doi":"https://doi.org/10.1177/1094342015580864","title":"Study of parallel programming models on computer clusters with Intel MIC coprocessors","display_name":"Study of parallel programming models on computer clusters with Intel MIC coprocessors","publication_year":2015,"publication_date":"2015-04-13","ids":{"openalex":"https://openalex.org/W2314584550","doi":"https://doi.org/10.1177/1094342015580864","mag":"2314584550"},"language":"en","primary_location":{"id":"doi:10.1177/1094342015580864","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1094342015580864","pdf_url":null,"source":{"id":"https://openalex.org/S60606485","display_name":"The International Journal of High Performance Computing Applications","issn_l":"1094-3420","issn":["1094-3420","1741-2846"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of High Performance Computing Applications","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/A5069173833","display_name":"Miaoqing Huang","orcid":"https://orcid.org/0000-0001-7376-3744"},"institutions":[{"id":"https://openalex.org/I78715868","display_name":"University of Arkansas at Fayetteville","ror":"https://ror.org/05jbt9m15","country_code":"US","type":"education","lineage":["https://openalex.org/I78715868"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Miaoqing Huang","raw_affiliation_strings":["University of Arkansas, Fayetteville, AR, USA"],"affiliations":[{"raw_affiliation_string":"University of Arkansas, Fayetteville, AR, USA","institution_ids":["https://openalex.org/I78715868"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055095462","display_name":"Chenggang Lai","orcid":null},"institutions":[{"id":"https://openalex.org/I78715868","display_name":"University of Arkansas at Fayetteville","ror":"https://ror.org/05jbt9m15","country_code":"US","type":"education","lineage":["https://openalex.org/I78715868"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chenggang Lai","raw_affiliation_strings":["University of Arkansas, Fayetteville, AR, USA"],"affiliations":[{"raw_affiliation_string":"University of Arkansas, Fayetteville, AR, USA","institution_ids":["https://openalex.org/I78715868"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101907238","display_name":"Xuan Shi","orcid":"https://orcid.org/0000-0002-1387-5418"},"institutions":[{"id":"https://openalex.org/I78715868","display_name":"University of Arkansas at Fayetteville","ror":"https://ror.org/05jbt9m15","country_code":"US","type":"education","lineage":["https://openalex.org/I78715868"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xuan Shi","raw_affiliation_strings":["University of Arkansas, Fayetteville, AR, USA"],"affiliations":[{"raw_affiliation_string":"University of Arkansas, Fayetteville, AR, USA","institution_ids":["https://openalex.org/I78715868"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040080165","display_name":"Zhijun Hao","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhijun Hao","raw_affiliation_strings":["Fudan University, Shanghai, P. R. China"],"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, P. R. China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017918038","display_name":"Haihang You","orcid":"https://orcid.org/0009-0005-9031-9430"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haihang You","raw_affiliation_strings":["Chinese Academy of Sciences, Beijing, P. R. China"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences, Beijing, P. R. China","institution_ids":["https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5069173833"],"corresponding_institution_ids":["https://openalex.org/I78715868"],"apc_list":null,"apc_paid":null,"fwci":1.9379,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.86762188,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"31","issue":"4","first_page":"303","last_page":"315"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9994999766349792,"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"}},{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.8637807369232178},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7808874249458313},{"id":"https://openalex.org/keywords/coprocessor","display_name":"Coprocessor","score":0.6835240721702576},{"id":"https://openalex.org/keywords/parallel-programming-model","display_name":"Parallel programming model","score":0.5952922105789185},{"id":"https://openalex.org/keywords/programming-paradigm","display_name":"Programming paradigm","score":0.5927094221115112},{"id":"https://openalex.org/keywords/xeon-phi","display_name":"Xeon Phi","score":0.5787827968597412},{"id":"https://openalex.org/keywords/message-passing-interface","display_name":"Message Passing Interface","score":0.5682487487792969},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.49689701199531555},{"id":"https://openalex.org/keywords/multithreading","display_name":"Multithreading","score":0.49575290083885193},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.47988688945770264},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.45429980754852295},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.4249360263347626},{"id":"https://openalex.org/keywords/message-passing","display_name":"Message passing","score":0.3579016923904419},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.35056859254837036},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3384353220462799},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.12876534461975098},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.11139044165611267}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8637807369232178},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7808874249458313},{"id":"https://openalex.org/C86111242","wikidata":"https://www.wikidata.org/wiki/Q859595","display_name":"Coprocessor","level":2,"score":0.6835240721702576},{"id":"https://openalex.org/C137364921","wikidata":"https://www.wikidata.org/wiki/Q27929394","display_name":"Parallel programming model","level":3,"score":0.5952922105789185},{"id":"https://openalex.org/C34165917","wikidata":"https://www.wikidata.org/wiki/Q188267","display_name":"Programming paradigm","level":2,"score":0.5927094221115112},{"id":"https://openalex.org/C96972482","wikidata":"https://www.wikidata.org/wiki/Q1049168","display_name":"Xeon Phi","level":2,"score":0.5787827968597412},{"id":"https://openalex.org/C166782233","wikidata":"https://www.wikidata.org/wiki/Q127879","display_name":"Message Passing Interface","level":3,"score":0.5682487487792969},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.49689701199531555},{"id":"https://openalex.org/C201410400","wikidata":"https://www.wikidata.org/wiki/Q1064412","display_name":"Multithreading","level":3,"score":0.49575290083885193},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.47988688945770264},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.45429980754852295},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.4249360263347626},{"id":"https://openalex.org/C854659","wikidata":"https://www.wikidata.org/wiki/Q1859284","display_name":"Message passing","level":2,"score":0.3579016923904419},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.35056859254837036},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3384353220462799},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.12876534461975098},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11139044165611267}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1177/1094342015580864","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1094342015580864","pdf_url":null,"source":{"id":"https://openalex.org/S60606485","display_name":"The International Journal of High Performance Computing Applications","issn_l":"1094-3420","issn":["1094-3420","1741-2846"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of High Performance Computing Applications","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.41999998688697815,"id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320310058","display_name":"University of Arkansas","ror":"https://ror.org/05jbt9m15"},{"id":"https://openalex.org/F4320338287","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1522731666","https://openalex.org/W1762731526","https://openalex.org/W1974037879","https://openalex.org/W1997751072","https://openalex.org/W2021836096","https://openalex.org/W2022867993","https://openalex.org/W2024344297","https://openalex.org/W2146390972","https://openalex.org/W2319224732","https://openalex.org/W3146239682","https://openalex.org/W4243099941"],"related_works":["https://openalex.org/W2213533160","https://openalex.org/W3203561460","https://openalex.org/W4252450863","https://openalex.org/W2467043670","https://openalex.org/W2022867993","https://openalex.org/W4294342484","https://openalex.org/W1554208380","https://openalex.org/W2682544458","https://openalex.org/W2051078434","https://openalex.org/W2283652387"],"abstract_inverted_index":{"Coprocessors":[0],"based":[1],"on":[2,29,44,73,116],"the":[3,34,45,50,58,74,81,87,98,111,149,174],"Intel":[4],"Many":[5],"Integrated":[6],"Core":[7],"(MIC)":[8],"Architecture":[9],"have":[10],"been":[11],"adopted":[12],"in":[13,159],"many":[14],"high-performance":[15],"computer":[16,60,117],"clusters.":[17],"Typical":[18],"parallel":[19,114],"programming":[20,55,71,83,101,157,177],"models,":[21],"such":[22],"as":[23,65,141,145],"MPI":[24,70,100,106,128,138,156,176],"and":[25,47,169],"OpenMP,":[26],"are":[27,64],"supported":[28],"MIC":[30,51,75,90,120,143,167],"processors":[31,52,76,144],"to":[32,89,135,140,147,165],"achieve":[33],"parallelism.":[35],"In":[36],"this":[37],"work,":[38],"we":[39],"conduct":[40],"a":[41,124,132],"detailed":[42],"study":[43],"performance":[46,112],"scalability":[48],"of":[49,97,127],"under":[53],"different":[54],"models":[56],"using":[57,92],"Beacon":[59],"cluster.":[61],"Our":[62],"findings":[63],"follows.":[66],"(1)":[67],"The":[68,154],"native":[69,99,175],"model":[72],"is":[77,131,163],"typically":[78],"better":[79],"than":[80],"offload":[82],"model,":[84,102,158],"which":[85,160],"offloads":[86],"workload":[88],"cores":[91,168],"OpenMP.":[93],"(2)":[94],"On":[95],"top":[96],"multithreading":[103],"inside":[104],"each":[105],"process":[107],"can":[108,172],"further":[109],"improve":[110],"for":[113],"applications":[115],"clusters":[118],"with":[119],"coprocessors.":[121],"(3)":[122],"Given":[123],"fixed":[125],"number":[126],"processes,":[129],"it":[130],"good":[133],"strategy":[134],"schedule":[136],"these":[137],"processes":[139],"few":[142],"possible":[146],"reduce":[148],"cross-processor":[150],"communication":[151],"overhead.":[152],"(4)":[153],"hybrid":[155],"data":[161],"processing":[162],"distributed":[164],"both":[166],"CPU":[170],"cores,":[171],"outperform":[173],"model.":[178]},"counts_by_year":[{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}