{"id":"https://openalex.org/W2061515180","doi":"https://doi.org/10.1109/hpcsim.2014.6903662","title":"Multi-Kepler GPU vs. multi-intel MIC: A two test case performance study","display_name":"Multi-Kepler GPU vs. multi-intel MIC: A two test case performance study","publication_year":2014,"publication_date":"2014-07-01","ids":{"openalex":"https://openalex.org/W2061515180","doi":"https://doi.org/10.1109/hpcsim.2014.6903662","mag":"2061515180"},"language":"en","primary_location":{"id":"doi:10.1109/hpcsim.2014.6903662","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpcsim.2014.6903662","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 International Conference on High Performance Computing & Simulation (HPCS)","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/A5006496977","display_name":"Massimo Bernaschi","orcid":"https://orcid.org/0000-0003-3661-9836"},"institutions":[{"id":"https://openalex.org/I4210106125","display_name":"Istituto per le Applicazioni del Calcolo Mauro Picone","ror":"https://ror.org/00ygy3d85","country_code":"IT","type":"facility","lineage":["https://openalex.org/I4210106125","https://openalex.org/I4210155236"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Massimo Bernaschi","raw_affiliation_strings":["Istituto Applicazioni Calcolo CNR Rome, Italy","Istituto Applicazioni Calcolo, CNR, Rome, Italy"],"affiliations":[{"raw_affiliation_string":"Istituto Applicazioni Calcolo CNR Rome, Italy","institution_ids":["https://openalex.org/I4210106125"]},{"raw_affiliation_string":"Istituto Applicazioni Calcolo, CNR, Rome, Italy","institution_ids":["https://openalex.org/I4210106125"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069613322","display_name":"Francesco Salvadore","orcid":"https://orcid.org/0000-0002-1829-3388"},"institutions":[{"id":"https://openalex.org/I4210119786","display_name":"Cineca","ror":"https://ror.org/02f013h18","country_code":"IT","type":"other","lineage":["https://openalex.org/I4210119786"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Francesco Salvadore","raw_affiliation_strings":["SuperComputing Applications and Innovation Department, Cineca Rome, Italy","SuperComputing Applications and Innovation Department, Cineca, Rome, Italy"],"affiliations":[{"raw_affiliation_string":"SuperComputing Applications and Innovation Department, Cineca Rome, Italy","institution_ids":["https://openalex.org/I4210119786"]},{"raw_affiliation_string":"SuperComputing Applications and Innovation Department, Cineca, Rome, Italy","institution_ids":["https://openalex.org/I4210119786"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5006496977"],"corresponding_institution_ids":["https://openalex.org/I4210106125"],"apc_list":null,"apc_paid":null,"fwci":0.55436274,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.70963113,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"182","issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9980000257492065,"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":0.9980000257492065,"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":0.9968000054359436,"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":0.9919000267982483,"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":0.7661681175231934},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6911134719848633},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6867417097091675},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6716424226760864},{"id":"https://openalex.org/keywords/coprocessor","display_name":"Coprocessor","score":0.6053521037101746},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.5256867408752441},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.5114144682884216},{"id":"https://openalex.org/keywords/instruction-set","display_name":"Instruction set","score":0.48259055614471436},{"id":"https://openalex.org/keywords/double-precision-floating-point-format","display_name":"Double-precision floating-point format","score":0.4244823455810547},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.26162469387054443},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.1373908817768097}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7661681175231934},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6911134719848633},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6867417097091675},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6716424226760864},{"id":"https://openalex.org/C86111242","wikidata":"https://www.wikidata.org/wiki/Q859595","display_name":"Coprocessor","level":2,"score":0.6053521037101746},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.5256867408752441},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.5114144682884216},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.48259055614471436},{"id":"https://openalex.org/C35912277","wikidata":"https://www.wikidata.org/wiki/Q1243369","display_name":"Double-precision floating-point format","level":3,"score":0.4244823455810547},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.26162469387054443},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1373908817768097},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","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/C84211073","wikidata":"https://www.wikidata.org/wiki/Q117879","display_name":"Floating point","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hpcsim.2014.6903662","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpcsim.2014.6903662","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 International Conference on High Performance Computing & Simulation (HPCS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","score":0.5099999904632568,"display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W348433680","https://openalex.org/W624975885","https://openalex.org/W1744184223","https://openalex.org/W1977671418","https://openalex.org/W1979413470","https://openalex.org/W1979899883","https://openalex.org/W2023755689","https://openalex.org/W2024830919","https://openalex.org/W2057848798","https://openalex.org/W2109206953","https://openalex.org/W2124119654","https://openalex.org/W2149173171","https://openalex.org/W6611841979"],"related_works":["https://openalex.org/W3145240193","https://openalex.org/W2147073383","https://openalex.org/W2540373069","https://openalex.org/W1578642488","https://openalex.org/W3189307731","https://openalex.org/W2949962288","https://openalex.org/W2020279179","https://openalex.org/W2364686214","https://openalex.org/W1428699136","https://openalex.org/W1998560227"],"abstract_inverted_index":{"We":[0],"present":[1],"and":[2,13,22,144],"compare":[3],"the":[4,10,14,27,39,48,56,73,90,113,125,131,134,147],"performances":[5,91,132],"of":[6,29,47,78,92,133],"two":[7,30],"many-core":[8],"architectures:":[9],"Nvidia":[11],"Kepler":[12],"Intel":[15,94,114],"MIC":[16,95],"both":[17],"in":[18,23,117],"a":[19,34,44,65,83,109],"single":[20,45,135],"system":[21],"cluster":[24,118],"configuration":[25,119],"for":[26,69,142,145],"simulation":[28],"physical":[31],"systems.":[32],"As":[33],"first":[35],"benchmark":[36],"we":[37,62,71],"consider":[38,63],"time":[40],"required":[41],"to":[42,82,107,123],"update":[43],"spin":[46,51],"3D":[49],"Heisenberg":[50],"glass":[52],"model":[53],"by":[54],"using":[55],"Over-relaxation":[57],"algorithm.":[58],"The":[59,86],"second":[60],"application":[61],"is":[64,105,121],"reactive":[66],"fluid-dynamics":[67],"problem":[68],"which":[70,129],"resolve":[72],"full":[74],"Navier-Stokes":[75],"compressible":[76],"set":[77],"equations":[79],"without":[80],"resorting":[81],"turbulence":[84],"model.":[85],"results":[87],"show":[88],"that":[89,106],"an":[93],"change":[96],"dramatically":[97],"depending":[98],"on":[99],"(apparently)":[100],"minor":[101],"details.":[102],"Another":[103],"issue":[104],"obtain":[108],"reasonable":[110],"scalability":[111],"with":[112],"Phi":[115],"coprocessor":[116],"it":[120],"necessary":[122],"use":[124],"so-called":[126],"offload":[127],"mode":[128],"reduces":[130],"system.":[136],"All":[137],"source":[138],"codes":[139],"are":[140],"provided":[141],"inspection":[143],"double-checking":[146],"results.":[148]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"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"}