{"id":"https://openalex.org/W4256213682","doi":"https://doi.org/10.1109/cgo.2015.7054205","title":"Locality-centric thread scheduling for bulk-synchronous programming models on CPU architectures","display_name":"Locality-centric thread scheduling for bulk-synchronous programming models on CPU architectures","publication_year":2015,"publication_date":"2015-02-01","ids":{"openalex":"https://openalex.org/W4256213682","doi":"https://doi.org/10.1109/cgo.2015.7054205"},"language":"en","primary_location":{"id":"doi:10.1109/cgo.2015.7054205","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cgo.2015.7054205","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE/ACM International Symposium on Code Generation and Optimization (CGO)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5036895130","display_name":"Hee-Seok Kim","orcid":"https://orcid.org/0000-0003-0099-7413"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hee-Seok Kim","raw_affiliation_strings":["University of Illinois at Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076404852","display_name":"Izzat El Hajj","orcid":"https://orcid.org/0000-0003-3356-6898"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Izzat El Hajj","raw_affiliation_strings":["University of Illinois at Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034958091","display_name":"John A. Stratton","orcid":"https://orcid.org/0000-0002-3625-9781"},"institutions":[{"id":"https://openalex.org/I39660569","display_name":"Colgate University","ror":"https://ror.org/05d23ve83","country_code":"US","type":"education","lineage":["https://openalex.org/I39660569"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John Stratton","raw_affiliation_strings":["Colgate University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Colgate University","institution_ids":["https://openalex.org/I39660569"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108619331","display_name":"Steven S. Lumetta","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Steven Lumetta","raw_affiliation_strings":["University of Illinois at Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040404999","display_name":"Wen\u2010mei Hwu","orcid":"https://orcid.org/0000-0003-2532-5349"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wen-Mei Hwu","raw_affiliation_strings":["University of Illinois at Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"23","issue":null,"first_page":"257","last_page":"268"},"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":0.9987999796867371,"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":0.9973999857902527,"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":0.9127377271652222},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6862014532089233},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.6185200810432434},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.5824311971664429},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.5237056016921997},{"id":"https://openalex.org/keywords/dataflow","display_name":"Dataflow","score":0.513654887676239},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.4716989994049072},{"id":"https://openalex.org/keywords/correctness","display_name":"Correctness","score":0.4165641665458679},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.4101629853248596},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.33335697650909424},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.31253287196159363},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.176161527633667}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9127377271652222},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6862014532089233},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.6185200810432434},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.5824311971664429},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5237056016921997},{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.513654887676239},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.4716989994049072},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.4165641665458679},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.4101629853248596},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.33335697650909424},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.31253287196159363},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.176161527633667},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cgo.2015.7054205","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cgo.2015.7054205","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE/ACM International Symposium on Code Generation and Optimization (CGO)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.4399999976158142}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W38257615","https://openalex.org/W1485193134","https://openalex.org/W1494930385","https://openalex.org/W1502558230","https://openalex.org/W1537233943","https://openalex.org/W1979527452","https://openalex.org/W1984303163","https://openalex.org/W1988888548","https://openalex.org/W1991009705","https://openalex.org/W1991592471","https://openalex.org/W1994316441","https://openalex.org/W2010936531","https://openalex.org/W2028914809","https://openalex.org/W2031781358","https://openalex.org/W2034761517","https://openalex.org/W2040142113","https://openalex.org/W2067479799","https://openalex.org/W2074185362","https://openalex.org/W2076485607","https://openalex.org/W2080592089","https://openalex.org/W2086698285","https://openalex.org/W2108315152","https://openalex.org/W2124556751","https://openalex.org/W2128046183","https://openalex.org/W2129232868","https://openalex.org/W2134705409","https://openalex.org/W2137081678","https://openalex.org/W2143798346","https://openalex.org/W2151195685","https://openalex.org/W2160875256","https://openalex.org/W2273440736","https://openalex.org/W2617756197","https://openalex.org/W3016205154","https://openalex.org/W3103903655","https://openalex.org/W3139083165","https://openalex.org/W3149591378","https://openalex.org/W3203568064","https://openalex.org/W4239609053","https://openalex.org/W6606521517","https://openalex.org/W6629835911","https://openalex.org/W6632052898","https://openalex.org/W6660462035","https://openalex.org/W6662005246","https://openalex.org/W6681006065","https://openalex.org/W6694513646","https://openalex.org/W6712805996"],"related_works":["https://openalex.org/W2293118914","https://openalex.org/W2998381397","https://openalex.org/W4236419692","https://openalex.org/W3167919718","https://openalex.org/W4251718783","https://openalex.org/W2171015181","https://openalex.org/W4239447582","https://openalex.org/W2040267466","https://openalex.org/W2102460670","https://openalex.org/W2025467172"],"abstract_inverted_index":{"With":[0],"heterogeneous":[1],"computing":[2],"on":[3,9,89,108,138,167],"the":[4,94,103,123],"rise,":[5],"executing":[6],"programs":[7],"efficiently":[8],"different":[10],"devices":[11],"from":[12],"a":[13,23,31,43,130],"single":[14],"source":[15],"code":[16],"has":[17,27,83],"become":[18],"increasingly":[19],"important.":[20],"OpenCL,":[21],"having":[22],"bulk-synchronous":[24],"programming":[25],"model,":[26],"been":[28,70,84],"proposed":[29],"as":[30],"framework":[32],"for":[33,72],"writing":[34],"such":[35],"performance-portable":[36],"programs.":[37],"Execution":[38],"order":[39],"of":[40,96,105,157],"work-items":[41,60,79,142],"in":[42,80,127],"program":[44],"is":[45],"unconstrained":[46],"except":[47],"at":[48],"barrier":[49],"synchronization":[50,62],"events,":[51],"giving":[52],"some":[53],"freedom":[54],"to":[55,140,143],"an":[56,113],"implementation":[57],"when":[58],"scheduling":[59,78,107],"between":[61],"points.":[63],"Many":[64],"OpenCL":[65,114],"(and":[66],"CUDA)":[67],"compilers":[68],"have":[69],"designed":[71],"targeting":[73],"multicore":[74],"CPU":[75],"architectures.":[76],"However,":[77],"prior":[81],"work":[82],"done":[85],"with":[86],"primary":[87],"focus":[88],"correctness":[90],"and":[91,161,169],"vectorization.":[92],"To":[93],"best":[95],"our":[97,132],"knowledge,":[98],"no":[99],"existing":[100],"implementations":[101,166],"consider":[102],"impact":[104],"work-item":[106,119],"data":[109],"locality.":[110],"We":[111],"propose":[112],"compiler":[115],"that":[116],"performs":[117],"data-locality-centric":[118],"scheduling.":[120],"By":[121],"analyzing":[122],"memory":[124,146],"addresses":[125],"accessed":[126],"loops":[128],"within":[129],"kernel,":[131],"technique":[133],"can":[134],"make":[135],"better":[136,145],"decisions":[137],"how":[139],"schedule":[141],"construct":[144],"access":[147],"patterns,":[148],"thereby":[149],"improving":[150],"performance.":[151],"Our":[152],"approach":[153],"achieves":[154],"geomean":[155],"speedups":[156],"3.32\u00d7":[158],"over":[159,164],"AMD's":[160],"1.71":[162],"\u00d7":[163],"Intel's":[165],"Parboil":[168],"Rodinia":[170],"benchmarks.":[171]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}