{"id":"https://openalex.org/W2312694346","doi":"https://doi.org/10.1109/hpca.2016.7446083","title":"Predicting the memory bandwidth and optimal core allocations for multi-threaded applications on large-scale NUMA machines","display_name":"Predicting the memory bandwidth and optimal core allocations for multi-threaded applications on large-scale NUMA machines","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2312694346","doi":"https://doi.org/10.1109/hpca.2016.7446083","mag":"2312694346"},"language":"en","primary_location":{"id":"doi:10.1109/hpca.2016.7446083","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpca.2016.7446083","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Symposium on High Performance Computer Architecture (HPCA)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://zenodo.org/record/1269327","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100392222","display_name":"Wei Wang","orcid":"https://orcid.org/0000-0003-2262-2508"},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Wei Wang","raw_affiliation_strings":["Department of Computer Science, University of Virginia"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Virginia","institution_ids":["https://openalex.org/I51556381"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068264173","display_name":"Jack W. Davidson","orcid":null},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jack W. Davidson","raw_affiliation_strings":["Department of Computer Science, University of Virginia"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Virginia","institution_ids":["https://openalex.org/I51556381"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047746948","display_name":"Mary Lou Soffa","orcid":"https://orcid.org/0000-0002-3665-7763"},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mary Lou Soffa","raw_affiliation_strings":["Department of Computer Science, University of Virginia"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Virginia","institution_ids":["https://openalex.org/I51556381"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100392222"],"corresponding_institution_ids":["https://openalex.org/I51556381"],"apc_list":null,"apc_paid":null,"fwci":5.7596,"has_fulltext":false,"cited_by_count":46,"citation_normalized_percentile":{"value":0.96359002,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"419","last_page":"431"},"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9934999942779541,"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"}},{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9915000200271606,"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":0.8739949464797974},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6818753480911255},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6810076832771301},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.5687519907951355},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.5330871939659119},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.5045405626296997},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.494021475315094},{"id":"https://openalex.org/keywords/memory-management","display_name":"Memory management","score":0.4779810309410095},{"id":"https://openalex.org/keywords/shared-memory","display_name":"Shared memory","score":0.4720609784126282},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.45533981919288635},{"id":"https://openalex.org/keywords/distributed-memory","display_name":"Distributed memory","score":0.4442746639251709},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.43141669034957886},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.11903908848762512},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.08380687236785889},{"id":"https://openalex.org/keywords/semiconductor-memory","display_name":"Semiconductor memory","score":0.08356189727783203}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8739949464797974},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6818753480911255},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6810076832771301},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.5687519907951355},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.5330871939659119},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5045405626296997},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.494021475315094},{"id":"https://openalex.org/C176649486","wikidata":"https://www.wikidata.org/wiki/Q2308807","display_name":"Memory management","level":3,"score":0.4779810309410095},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.4720609784126282},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.45533981919288635},{"id":"https://openalex.org/C91481028","wikidata":"https://www.wikidata.org/wiki/Q1054686","display_name":"Distributed memory","level":3,"score":0.4442746639251709},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.43141669034957886},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.11903908848762512},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.08380687236785889},{"id":"https://openalex.org/C98986596","wikidata":"https://www.wikidata.org/wiki/Q1143031","display_name":"Semiconductor memory","level":2,"score":0.08356189727783203}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/hpca.2016.7446083","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpca.2016.7446083","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Symposium on High Performance Computer Architecture (HPCA)","raw_type":"proceedings-article"},{"id":"pmh:oai:zenodo.org:1269327","is_oa":true,"landing_page_url":"https://zenodo.org/record/1269327","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferencePaper"}],"best_oa_location":{"id":"pmh:oai:zenodo.org:1269327","is_oa":true,"landing_page_url":"https://zenodo.org/record/1269327","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferencePaper"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6207218579","display_name":"CPA-CPL-T: Collaborative Research:  REEact:  A Robust Execution Environment for Fragile Multicore Systems","funder_award_id":"0811689","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8878848345","display_name":"CSR: Medium: Collaborative Research: Scaling the Implicitly Parallel Programming Model with Lifelong Thread Extraction and Dynamic Adaptation","funder_award_id":"0964627","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320338294","display_name":"Air Force Research Laboratory","ror":"https://ror.org/02e2egq70"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":70,"referenced_works":["https://openalex.org/W35708471","https://openalex.org/W1086484114","https://openalex.org/W1510263988","https://openalex.org/W1598342322","https://openalex.org/W1938553034","https://openalex.org/W1965771437","https://openalex.org/W1980582286","https://openalex.org/W1982632559","https://openalex.org/W1993711049","https://openalex.org/W1998559030","https://openalex.org/W2014328192","https://openalex.org/W2016210396","https://openalex.org/W2016414291","https://openalex.org/W2033875825","https://openalex.org/W2036403064","https://openalex.org/W2048441570","https://openalex.org/W2056267751","https://openalex.org/W2067441262","https://openalex.org/W2067801022","https://openalex.org/W2072001046","https://openalex.org/W2072298242","https://openalex.org/W2076491133","https://openalex.org/W2081131254","https://openalex.org/W2084903759","https://openalex.org/W2089229046","https://openalex.org/W2100787464","https://openalex.org/W2101360724","https://openalex.org/W2105321788","https://openalex.org/W2105506259","https://openalex.org/W2106342588","https://openalex.org/W2107277872","https://openalex.org/W2109515201","https://openalex.org/W2114616381","https://openalex.org/W2119438786","https://openalex.org/W2125623590","https://openalex.org/W2130672783","https://openalex.org/W2131312592","https://openalex.org/W2132416440","https://openalex.org/W2143735977","https://openalex.org/W2145892830","https://openalex.org/W2148896195","https://openalex.org/W2149381887","https://openalex.org/W2151233837","https://openalex.org/W2151326614","https://openalex.org/W2154565673","https://openalex.org/W2154713585","https://openalex.org/W2157216158","https://openalex.org/W2157802978","https://openalex.org/W2159456929","https://openalex.org/W2168102371","https://openalex.org/W2169665207","https://openalex.org/W2175443198","https://openalex.org/W2313882406","https://openalex.org/W2568452623","https://openalex.org/W2949437739","https://openalex.org/W3010639757","https://openalex.org/W3137551601","https://openalex.org/W3147501999","https://openalex.org/W3148542938","https://openalex.org/W4237161200","https://openalex.org/W4285719527","https://openalex.org/W4300124530","https://openalex.org/W6630776666","https://openalex.org/W6635822831","https://openalex.org/W6669459168","https://openalex.org/W6675438776","https://openalex.org/W6675903601","https://openalex.org/W6684730004","https://openalex.org/W6844032363","https://openalex.org/W6981805521"],"related_works":["https://openalex.org/W2026512611","https://openalex.org/W1985165680","https://openalex.org/W4245497162","https://openalex.org/W2031026393","https://openalex.org/W2353146130","https://openalex.org/W254684032","https://openalex.org/W4291801887","https://openalex.org/W1824582190","https://openalex.org/W120214571","https://openalex.org/W1848192231"],"abstract_inverted_index":{"Modern":[0],"NUMA":[1,79,105,143,160,203],"platforms":[2],"offer":[3],"large":[4],"numbers":[5,65,95],"of":[6,27,63,66,76,96],"cores":[7,30,177,181],"to":[8,113,149],"boost":[9],"performance":[10,17],"through":[11],"parallelism":[12],"and":[13,44,82,133,142,145,153,187,206],"multi-threading.":[14],"However,":[15,68],"because":[16,75],"scalability":[18],"is":[19],"limited":[20],"by":[21,168],"available":[22],"memory":[23,80,86,106,130,140,204,208],"bandwidth,":[24],"the":[25,54,61,77,83,164],"strategy":[26],"allocating":[28],"all":[29,176],"can":[31],"result":[32],"in":[33,69],"degraded":[34],"performance.":[35,56],"Consequently,":[36],"accurately":[37,114],"predicting":[38],"optimal":[39,64,88,94,116,134],"(best":[40],"performing)":[41],"core":[42,89,117,135,165],"allocations,":[43],"executing":[45],"applications":[46],"with":[47,178,211],"these":[48],"allocations":[49,90,166],"are":[50,91],"crucial":[51],"for":[52],"achieving":[53],"best":[55],"Previous":[57],"research":[58],"focused":[59],"on":[60],"prediction":[62],"cores.":[67,97],"this":[70,120],"paper,":[71,121],"we":[72,122],"show":[73,162,198],"that,":[74],"asymmetric":[78,84],"configuration":[81],"application":[85],"behavior,":[87],"not":[92,102],"merely":[93],"Additionally,":[98],"previous":[99],"studies":[100],"do":[101],"adequately":[103],"consider":[104],"resources,":[107],"which":[108,127],"further":[109],"limits":[110],"their":[111],"ability":[112],"predict":[115],"allocations.":[118,136],"In":[119],"present":[123],"a":[124],"model,":[125],"NuCore,":[126],"predicts":[128,207],"both":[129],"bandwidth":[131,209],"usage":[132],"NuCore":[137,169,183,200],"considers":[138],"various":[139],"resources":[141],"asymmetry,":[144],"employs":[146],"Integer":[147],"Programming":[148],"achieve":[150],"high":[151],"accuracy":[152],"low":[154],"overhead.":[155],"Experimental":[156],"results":[157,196],"from":[158],"real":[159],"machines":[161],"that":[163,199],"predicted":[167],"provide":[170],"1.27x":[171],"average":[172,189,214],"speedup":[173],"over":[174,191],"using":[175],"only":[179,212],"75.6%":[180],"allocated.":[182],"also":[184,197],"provides":[185],"1.18x":[186],"1.21x":[188],"speedups":[190],"two":[192],"state-of-the-art":[193],"techniques.":[194],"Our":[195],"faithfully":[201],"models":[202],"systems":[205],"usages":[210],"10%":[213],"error.":[215]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":9},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":3}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}