{"id":"https://openalex.org/W2173933029","doi":"https://doi.org/10.1145/2381056.2381079","title":"Critical path-based thread placement for NUMA systems","display_name":"Critical path-based thread placement for NUMA systems","publication_year":2012,"publication_date":"2012-10-08","ids":{"openalex":"https://openalex.org/W2173933029","doi":"https://doi.org/10.1145/2381056.2381079","mag":"2173933029"},"language":"en","primary_location":{"id":"doi:10.1145/2381056.2381079","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2381056.2381079","pdf_url":null,"source":{"id":"https://openalex.org/S4210187660","display_name":"ACM SIGMETRICS Performance Evaluation Review","issn_l":"0163-5999","issn":["0163-5999","1557-9484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM SIGMETRICS Performance Evaluation Review","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://digital.library.unt.edu/ark:/67531/metadc843606/m2/1/high_res_d/1035298.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5006363358","display_name":"Chun-Yi Su","orcid":null},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"ChunYi Su","raw_affiliation_strings":["Virginia Tech, Blacksburg, VA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Virginia Tech, Blacksburg, VA, USA","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100407387","display_name":"Dong Li","orcid":"https://orcid.org/0000-0001-9336-0694"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dong Li","raw_affiliation_strings":["Oak Ridge National Lab, Oak Ridge, TN, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oak Ridge National Lab, Oak Ridge, TN, USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005410613","display_name":"Dimitrios S. Nikolopoulos","orcid":"https://orcid.org/0000-0003-0217-8307"},"institutions":[{"id":"https://openalex.org/I8901234","display_name":"Foundation for Research and Technology Hellas","ror":"https://ror.org/052rphn09","country_code":"GR","type":"facility","lineage":["https://openalex.org/I8901234"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Dimitrios S. Nikolopoulos","raw_affiliation_strings":["FORTH-ICS, Heraklion, Crete, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"FORTH-ICS, Heraklion, Crete, Greece","institution_ids":["https://openalex.org/I8901234"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088799818","display_name":"Matthew Grove","orcid":null},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matthew Grove","raw_affiliation_strings":["Virginia Tech, Blacksburg, VA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Virginia Tech, Blacksburg, VA, USA","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019476126","display_name":"Kirk W. Cameron","orcid":"https://orcid.org/0000-0002-1679-5448"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kirk Cameron","raw_affiliation_strings":["Virginia Tech, Blacksburg, VA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Virginia Tech, Blacksburg, VA, USA","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058719424","display_name":"Bronis R. de Supinski","orcid":"https://orcid.org/0000-0002-0339-1006"},"institutions":[{"id":"https://openalex.org/I4210138311","display_name":"Lawrence Livermore National Security","ror":"https://ror.org/03z21mf61","country_code":"US","type":"government","lineage":["https://openalex.org/I4210138311"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bronis R. de Supinski","raw_affiliation_strings":["LLNL, Livermore, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LLNL, Livermore, CA, USA","institution_ids":["https://openalex.org/I4210138311"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.4237,"has_fulltext":true,"cited_by_count":19,"citation_normalized_percentile":{"value":0.95674387,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"40","issue":"2","first_page":"106","last_page":"112"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":1.0,"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":1.0,"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":0.9995999932289124,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9988999962806702,"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":0.889741063117981},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.8198422193527222},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7343391180038452},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7294469475746155},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.5164099335670471},{"id":"https://openalex.org/keywords/shared-memory","display_name":"Shared memory","score":0.4385567009449005},{"id":"https://openalex.org/keywords/critical-path-method","display_name":"Critical path method","score":0.4179025888442993},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.38213154673576355},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.34641218185424805}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.889741063117981},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.8198422193527222},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7343391180038452},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7294469475746155},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.5164099335670471},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.4385567009449005},{"id":"https://openalex.org/C115874739","wikidata":"https://www.wikidata.org/wiki/Q825377","display_name":"Critical path method","level":2,"score":0.4179025888442993},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.38213154673576355},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.34641218185424805},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/2381056.2381079","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2381056.2381079","pdf_url":null,"source":{"id":"https://openalex.org/S4210187660","display_name":"ACM SIGMETRICS Performance Evaluation Review","issn_l":"0163-5999","issn":["0163-5999","1557-9484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM SIGMETRICS Performance Evaluation Review","raw_type":"journal-article"},{"id":"pmh:info:ark/67531/metadc843606","is_oa":true,"landing_page_url":"https://digital.library.unt.edu/ark:/67531/metadc843606/","pdf_url":"https://digital.library.unt.edu/ark:/67531/metadc843606/m2/1/high_res_d/1035298.pdf","source":{"id":"https://openalex.org/S4306400792","display_name":"University of North Texas Digital Library (University of North Texas)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I123534392","host_organization_name":"University of North Texas","host_organization_lineage":["https://openalex.org/I123534392"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Presented at: 2nd International Workshop on Performance Modeling, Benchmarking and Simulation of High Performance Computing Systems (PMBS11), Seattle, WA, United States, Nov 13 - Nov 13, 2011","raw_type":"Article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.306.6468","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.306.6468","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://scape.cs.vt.edu/wp-content/uploads/2012/08/pmbs-2011-workshop.pdf","raw_type":"text"},{"id":"pmh:oai:pure.qub.ac.uk/portal:publications/d1e3feff-922b-4e54-aa6d-45ff7c7d65f9","is_oa":false,"landing_page_url":"https://pure.qub.ac.uk/en/publications/d1e3feff-922b-4e54-aa6d-45ff7c7d65f9","pdf_url":null,"source":{"id":"https://openalex.org/S4306402319","display_name":"Research Portal (Queen's University Belfast)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I126231945","host_organization_name":"Queen's University Belfast","host_organization_lineage":["https://openalex.org/I126231945"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Su , C-Y , Li , D , Nikolopoulos , D , Grove , M , Cameron , K W &amp; De Supinski , B 2012 , ' Critical Path-Based Thread Placement for NUMA Systems ' , ACM SIGMETRICS Performance Evaluation Review , vol. 40 , no. 2 , pp. 106-112 . https://doi.org/10.1145/2381056.2381079","raw_type":"article"}],"best_oa_location":{"id":"pmh:info:ark/67531/metadc843606","is_oa":true,"landing_page_url":"https://digital.library.unt.edu/ark:/67531/metadc843606/","pdf_url":"https://digital.library.unt.edu/ark:/67531/metadc843606/m2/1/high_res_d/1035298.pdf","source":{"id":"https://openalex.org/S4306400792","display_name":"University of North Texas Digital Library (University of North Texas)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I123534392","host_organization_name":"University of North Texas","host_organization_lineage":["https://openalex.org/I123534392"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Presented at: 2nd International Workshop on Performance Modeling, Benchmarking and Simulation of High Performance Computing Systems (PMBS11), Seattle, WA, United States, Nov 13 - Nov 13, 2011","raw_type":"Article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2173933029.pdf","grobid_xml":"https://content.openalex.org/works/W2173933029.grobid-xml"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W22490863","https://openalex.org/W1607051734","https://openalex.org/W1963637299","https://openalex.org/W2032136713","https://openalex.org/W2040392157","https://openalex.org/W2079777558","https://openalex.org/W2098278566","https://openalex.org/W2102490737","https://openalex.org/W2113283471","https://openalex.org/W2125904114","https://openalex.org/W2132260309","https://openalex.org/W2157443293","https://openalex.org/W2169665207","https://openalex.org/W4240262711"],"related_works":["https://openalex.org/W3011443213","https://openalex.org/W298517545","https://openalex.org/W4312291060","https://openalex.org/W127342102","https://openalex.org/W3157359390","https://openalex.org/W2351616294","https://openalex.org/W2264746079","https://openalex.org/W1987160526","https://openalex.org/W1979099492","https://openalex.org/W4205439893"],"abstract_inverted_index":{"Multicore":[0],"multiprocessors":[1],"use":[2],"a":[3,53,95],"Non":[4],"Uniform":[5],"Memory":[6],"Architecture":[7],"(NUMA)":[8],"to":[9,19,31,132],"improve":[10],"their":[11],"scalability.":[12],"However,":[13],"NUMA":[14,64],"introduces":[15],"performance":[16,37,80,129],"penalties":[17,81],"due":[18],"remote":[20],"memory":[21],"accesses.":[22],"Without":[23],"efficiently":[24],"managing":[25],"data":[26],"layout":[27],"and":[28,52,78,109,127],"thread":[29,76,136,144],"mapping":[30],"cores,":[32],"scientific":[33],"applications":[34,62,116],"may":[35],"suffer":[36],"loss,":[38],"even":[39],"if":[40],"they":[41],"are":[42],"optimized":[43],"for":[44],"NUMA.":[45],"In":[46],"this":[47],"paper,":[48],"we":[49],"present":[50],"algorithms":[51,108,123,140],"runtime":[54,73,92,111],"system":[55,74,93,112],"that":[56,98],"optimize":[57],"the":[58,72,84,110,122,133,142,150],"execution":[59],"of":[60,87,149],"OpenMP":[61,88],"on":[63],"architectures.":[65],"By":[66],"collecting":[67],"information":[68],"from":[69],"hardware":[70],"counters,":[71],"directs":[75],"placement":[77,100,137,145],"reduces":[79],"by":[82],"minimizing":[83],"critical":[85],"path":[86],"parallel":[89],"regions.":[90],"The":[91,139],"uses":[94],"scalable":[96],"algorithm":[97],"derives":[99],"decisions":[101],"with":[102,113],"negligible":[103],"overhead.":[104],"We":[105],"evaluate":[106],"our":[107],"four":[114],"NPB":[115],"implemented":[117],"in":[118,146],"OpenMP.":[119],"On":[120],"average":[121],"achieve":[124],"between":[125],"8.13%":[126],"25.68%":[128],"improvement,":[130],"compared":[131],"default":[134],"Linux":[135],"scheme.":[138],"miss":[141],"optimal":[143],"only":[147],"8.9%":[148],"cases.":[151]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":3}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}
