{"id":"https://openalex.org/W1977871529","doi":"https://doi.org/10.1093/comjnl/bxv022","title":"Realistic Performance Characterization of CFD Applications on Intel Many Integrated Core Architecture","display_name":"Realistic Performance Characterization of CFD Applications on Intel Many Integrated Core Architecture","publication_year":2015,"publication_date":"2015-04-09","ids":{"openalex":"https://openalex.org/W1977871529","doi":"https://doi.org/10.1093/comjnl/bxv022","mag":"1977871529"},"language":"en","primary_location":{"id":"doi:10.1093/comjnl/bxv022","is_oa":false,"landing_page_url":"https://doi.org/10.1093/comjnl/bxv022","pdf_url":null,"source":{"id":"https://openalex.org/S44643521","display_name":"The Computer Journal","issn_l":"0010-4620","issn":["0010-4620","1460-2067"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Computer Journal","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/A5100889262","display_name":"Yonggang Che","orcid":null},"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":"Yonggang Che","raw_affiliation_strings":["Science and Technology on Parallel and Distributed Processing Laboratory (PDL), National University of Defense Technology, Changsha 410073, P. R. China"],"affiliations":[{"raw_affiliation_string":"Science and Technology on Parallel and Distributed Processing Laboratory (PDL), National University of Defense Technology, Changsha 410073, P. R. China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059351590","display_name":"Chuanfu Xu","orcid":"https://orcid.org/0000-0002-4876-2368"},"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":"Chuanfu Xu","raw_affiliation_strings":["Science and Technology on Parallel and Distributed Processing Laboratory (PDL), National University of Defense Technology, Changsha 410073, P. R. China"],"affiliations":[{"raw_affiliation_string":"Science and Technology on Parallel and Distributed Processing Laboratory (PDL), National University of Defense Technology, Changsha 410073, P. R. China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083171604","display_name":"Jianbin Fang","orcid":"https://orcid.org/0000-0003-3542-4869"},"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":"Jianbin Fang","raw_affiliation_strings":["Science and Technology on Parallel and Distributed Processing Laboratory (PDL), National University of Defense Technology, Changsha 410073, P. R. China"],"affiliations":[{"raw_affiliation_string":"Science and Technology on Parallel and Distributed Processing Laboratory (PDL), National University of Defense Technology, Changsha 410073, P. R. China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034520237","display_name":"Yongxian Wang","orcid":"https://orcid.org/0000-0002-6752-0436"},"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":"Yongxian Wang","raw_affiliation_strings":["Science and Technology on Parallel and Distributed Processing Laboratory (PDL), National University of Defense Technology, Changsha 410073, P. R. China"],"affiliations":[{"raw_affiliation_string":"Science and Technology on Parallel and Distributed Processing Laboratory (PDL), National University of Defense Technology, Changsha 410073, P. R. China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103183144","display_name":"Zhenghua Wang","orcid":"https://orcid.org/0000-0002-3757-1371"},"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":"Zhenghua Wang","raw_affiliation_strings":["Science and Technology on Parallel and Distributed Processing Laboratory (PDL), National University of Defense Technology, Changsha 410073, P. R. China"],"affiliations":[{"raw_affiliation_string":"Science and Technology on Parallel and Distributed Processing Laboratory (PDL), National University of Defense Technology, Changsha 410073, P. R. China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100889262"],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":{"value":2635,"currency":"GBP","value_usd":3232},"apc_paid":null,"fwci":2.9068,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.90646121,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"58","issue":"12","first_page":"3279","last_page":"3294"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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":0.998199999332428,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9980000257492065,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8512202501296997},{"id":"https://openalex.org/keywords/xeon-phi","display_name":"Xeon Phi","score":0.8058386445045471},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7753700017929077},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7398501634597778},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.7204716205596924},{"id":"https://openalex.org/keywords/coprocessor","display_name":"Coprocessor","score":0.6969091892242432},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6506881713867188},{"id":"https://openalex.org/keywords/multithreading","display_name":"Multithreading","score":0.6315578818321228},{"id":"https://openalex.org/keywords/xeon","display_name":"Xeon","score":0.5401531457901001},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.5327268838882446},{"id":"https://openalex.org/keywords/computational-fluid-dynamics","display_name":"Computational fluid dynamics","score":0.49892091751098633},{"id":"https://openalex.org/keywords/instruction-set","display_name":"Instruction set","score":0.4805748462677002},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.42209237813949585},{"id":"https://openalex.org/keywords/floating-point","display_name":"Floating point","score":0.417213499546051},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.4128863513469696},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.3063918352127075}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8512202501296997},{"id":"https://openalex.org/C96972482","wikidata":"https://www.wikidata.org/wiki/Q1049168","display_name":"Xeon Phi","level":2,"score":0.8058386445045471},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7753700017929077},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7398501634597778},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.7204716205596924},{"id":"https://openalex.org/C86111242","wikidata":"https://www.wikidata.org/wiki/Q859595","display_name":"Coprocessor","level":2,"score":0.6969091892242432},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6506881713867188},{"id":"https://openalex.org/C201410400","wikidata":"https://www.wikidata.org/wiki/Q1064412","display_name":"Multithreading","level":3,"score":0.6315578818321228},{"id":"https://openalex.org/C145108525","wikidata":"https://www.wikidata.org/wiki/Q656154","display_name":"Xeon","level":2,"score":0.5401531457901001},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.5327268838882446},{"id":"https://openalex.org/C1633027","wikidata":"https://www.wikidata.org/wiki/Q815820","display_name":"Computational fluid dynamics","level":2,"score":0.49892091751098633},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.4805748462677002},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.42209237813949585},{"id":"https://openalex.org/C84211073","wikidata":"https://www.wikidata.org/wiki/Q117879","display_name":"Floating point","level":2,"score":0.417213499546051},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.4128863513469696},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3063918352127075},{"id":"https://openalex.org/C57879066","wikidata":"https://www.wikidata.org/wiki/Q41217","display_name":"Mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1093/comjnl/bxv022","is_oa":false,"landing_page_url":"https://doi.org/10.1093/comjnl/bxv022","pdf_url":null,"source":{"id":"https://openalex.org/S44643521","display_name":"The Computer Journal","issn_l":"0010-4620","issn":["0010-4620","1460-2067"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Computer Journal","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320324150","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11"},{"id":"https://openalex.org/F4320337393","display_name":"Division of Chemistry","ror":"https://ror.org/01ar8dr59"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W86802742","https://openalex.org/W348433680","https://openalex.org/W787130922","https://openalex.org/W1596846800","https://openalex.org/W1909906732","https://openalex.org/W1981202981","https://openalex.org/W2002555321","https://openalex.org/W2016357834","https://openalex.org/W2024639384","https://openalex.org/W2046825786","https://openalex.org/W2065582878","https://openalex.org/W2086439318","https://openalex.org/W2091941628","https://openalex.org/W2109094156","https://openalex.org/W2115215129","https://openalex.org/W2139927851","https://openalex.org/W2269751313","https://openalex.org/W2315822413","https://openalex.org/W2327509351","https://openalex.org/W2356071242","https://openalex.org/W2382229033","https://openalex.org/W2467043670","https://openalex.org/W4251569789"],"related_works":["https://openalex.org/W2213533160","https://openalex.org/W4252450863","https://openalex.org/W2467043670","https://openalex.org/W2085105049","https://openalex.org/W2003336045","https://openalex.org/W3203561460","https://openalex.org/W2682544458","https://openalex.org/W3009624197","https://openalex.org/W2188798380","https://openalex.org/W1953299766"],"abstract_inverted_index":{"This":[0],"paper":[1],"studies":[2],"the":[3,34,43,55,63,71,74,95,103,107,112,116,153,177,182,186,190],"performance":[4,175,193],"characteristics":[5],"of":[6,47,57,90,135],"computational":[7],"fluid":[8],"dynamics":[9],"(CFD)":[10],"applications":[11,49,119,171],"on":[12,28,176,181],"Intel":[13,29],"Many":[14],"Integrated":[15],"Core":[16],"(MIC)":[17],"architecture.":[18],"Three":[19],"CFD":[20,118],"applications,":[21],"BT-MZ,":[22],"LM3D":[23],"and":[24,106,125,149,189],"HOSTA,":[25],"are":[26],"evaluated":[27],"Knights":[30],"Corner":[31],"(KNC)":[32],"coprocessor,":[33],"first":[35],"public":[36],"MIC":[37,178],"product.":[38],"The":[39,87],"results":[40],"show":[41],"that":[42],"pure":[44],"OpenMP":[45,96],"scalability":[46,188],"these":[48,170],"is":[50,83,99,198],"not":[51,85,100,151],"sufficient":[52],"to":[53,69,79,102,172],"utilize":[54,152],"potential":[56],"a":[58,80,132,159,199],"KNC":[59],"coprocessor.":[60],"While":[61],"utilizing":[62],"hybrid":[64,108],"MPI/OpenMP":[65,109],"programming":[66],"model":[67],"helps":[68],"improve":[70],"parallel":[72,76,187],"scalability,":[73],"maximum":[75],"speedup":[77],"relative":[78],"single":[81,165,191],"thread":[82,166,192],"still":[84],"satisfactory.":[86],"OpenCL":[88],"version":[89,97,105],"BT-MZ":[91],"performs":[92],"better":[93],"than":[94],"but":[98],"comparable":[101],"MPI":[104],"version.":[110],"At":[111],"micro-architecture":[113],"level,":[114],"while":[115],"three":[117],"achieve":[120,162],"reasonable":[121],"instruction":[122],"execution":[123],"rates":[124,148],"L1":[126],"data":[127],"cache":[128],"hit":[129],"rates,":[130],"use":[131],"large":[133],"percent":[134],"vector":[136],"instructions,":[137],"they":[138,161],"have":[139],"low":[140,164],"arithmetic":[141],"density,":[142],"incur":[143],"very":[144,163],"high":[145],"branch":[146],"misprediction":[147],"do":[150],"Vector":[154],"Processing":[155],"Unit":[156],"efficiently.":[157],"As":[158],"result,":[160],"floating-point":[167],"efficiency.":[168],"For":[169],"attain":[173],"competitive":[174],"architecture":[179],"as":[180],"Xeon":[183],"processors,":[184],"both":[185],"should":[194],"be":[195],"improved,":[196],"which":[197],"difficult":[200],"task.":[201]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}