{"id":"https://openalex.org/W2202621926","doi":"https://doi.org/10.1145/2766450","title":"Locality-Aware Work Stealing Based on Online Profiling and Auto-Tuning for Multisocket Multicore Architectures","display_name":"Locality-Aware Work Stealing Based on Online Profiling and Auto-Tuning for Multisocket Multicore Architectures","publication_year":2015,"publication_date":"2015-07-08","ids":{"openalex":"https://openalex.org/W2202621926","doi":"https://doi.org/10.1145/2766450","mag":"2202621926"},"language":"en","primary_location":{"id":"doi:10.1145/2766450","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2766450","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/2766450?download=true","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"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 Transactions on Architecture and Code Optimization","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/2766450?download=true","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100377840","display_name":"Quan Chen","orcid":"https://orcid.org/0000-0001-5832-0347"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Quan Chen","raw_affiliation_strings":["School of Software Engineering, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"School of Software Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039318240","display_name":"Minyi Guo","orcid":"https://orcid.org/0000-0003-0034-2302"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Minyi Guo","raw_affiliation_strings":["Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100377840"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":1.319,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.8119171,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"12","issue":"2","first_page":"1","last_page":"24"},"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9997000098228455,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9994999766349792,"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":0.9103788137435913},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.7517282366752625},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6496052742004395},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.6149462461471558},{"id":"https://openalex.org/keywords/cache-only-memory-architecture","display_name":"Cache-only memory architecture","score":0.5383599400520325},{"id":"https://openalex.org/keywords/allocator","display_name":"Allocator","score":0.5078430771827698},{"id":"https://openalex.org/keywords/translation-lookaside-buffer","display_name":"Translation lookaside buffer","score":0.5023422241210938},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.4836905598640442},{"id":"https://openalex.org/keywords/shared-memory","display_name":"Shared memory","score":0.4471474289894104},{"id":"https://openalex.org/keywords/cpu-cache","display_name":"CPU cache","score":0.43123728036880493},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.42892566323280334},{"id":"https://openalex.org/keywords/cache-coloring","display_name":"Cache coloring","score":0.30177944898605347},{"id":"https://openalex.org/keywords/physical-address","display_name":"Physical address","score":0.10087081789970398}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9103788137435913},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.7517282366752625},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6496052742004395},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.6149462461471558},{"id":"https://openalex.org/C3720319","wikidata":"https://www.wikidata.org/wiki/Q5015937","display_name":"Cache-only memory architecture","level":5,"score":0.5383599400520325},{"id":"https://openalex.org/C162262903","wikidata":"https://www.wikidata.org/wiki/Q343527","display_name":"Allocator","level":2,"score":0.5078430771827698},{"id":"https://openalex.org/C116007543","wikidata":"https://www.wikidata.org/wiki/Q1071403","display_name":"Translation lookaside buffer","level":4,"score":0.5023422241210938},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.4836905598640442},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.4471474289894104},{"id":"https://openalex.org/C189783530","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"CPU cache","level":3,"score":0.43123728036880493},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.42892566323280334},{"id":"https://openalex.org/C201148951","wikidata":"https://www.wikidata.org/wiki/Q5015976","display_name":"Cache coloring","level":4,"score":0.30177944898605347},{"id":"https://openalex.org/C41036726","wikidata":"https://www.wikidata.org/wiki/Q844824","display_name":"Physical address","level":3,"score":0.10087081789970398},{"id":"https://openalex.org/C136085584","wikidata":"https://www.wikidata.org/wiki/Q910289","display_name":"Overlay","level":2,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2766450","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2766450","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/2766450?download=true","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"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 Transactions on Architecture and Code Optimization","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/2766450","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2766450","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/2766450?download=true","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"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 Transactions on Architecture and Code Optimization","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1121271761","display_name":null,"funder_award_id":"Program","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1442181680","display_name":null,"funder_award_id":"PIRSES-GA-2012-318939","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G1912994486","display_name":null,"funder_award_id":"1150420","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2343379331","display_name":null,"funder_award_id":"2015CB352403","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G2787971126","display_name":null,"funder_award_id":"6126116050","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3151526626","display_name":null,"funder_award_id":"PCSIRT","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G372256174","display_name":null,"funder_award_id":"13511504200","funder_id":"https://openalex.org/F4320321885","funder_display_name":"Science and Technology Commission of Shanghai Municipality"},{"id":"https://openalex.org/G391238517","display_name":null,"funder_award_id":", and","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4005836112","display_name":null,"funder_award_id":"61261160502","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4166410561","display_name":null,"funder_award_id":"61272099","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5588543288","display_name":null,"funder_award_id":"PIRSES-GA-2012-318939","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5653694092","display_name":null,"funder_award_id":"2015CB352403","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6566408951","display_name":null,"funder_award_id":"11504200","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G662609344","display_name":null,"funder_award_id":"IRT1158","funder_id":"https://openalex.org/F4320338204","funder_display_name":"Program for Changjiang Scholars and Innovative Research Team in University"},{"id":"https://openalex.org/G6897229319","display_name":null,"funder_award_id":"PCSIRT","funder_id":"https://openalex.org/F4320338204","funder_display_name":"Program for Changjiang Scholars and Innovative Research Team in University"},{"id":"https://openalex.org/G6965955227","display_name":null,"funder_award_id":"2012-3","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7697891380","display_name":null,"funder_award_id":"IRT1158","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8532262400","display_name":null,"funder_award_id":"61261160502, 61272099","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G875995759","display_name":null,"funder_award_id":"IRT1158, PCSIRT","funder_id":"https://openalex.org/F4320338204","funder_display_name":"Program for Changjiang Scholars and Innovative Research Team in University"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321885","display_name":"Science and Technology Commission of Shanghai Municipality","ror":"https://ror.org/03kt66j61"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null},{"id":"https://openalex.org/F4320338204","display_name":"Program for Changjiang Scholars and Innovative Research Team in University","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2202621926.pdf","grobid_xml":"https://content.openalex.org/works/W2202621926.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W940080019","https://openalex.org/W1536852470","https://openalex.org/W1773176621","https://openalex.org/W1885398124","https://openalex.org/W1914552515","https://openalex.org/W1986864222","https://openalex.org/W1994909161","https://openalex.org/W1995873479","https://openalex.org/W2026842524","https://openalex.org/W2032401773","https://openalex.org/W2043331236","https://openalex.org/W2055099017","https://openalex.org/W2063270401","https://openalex.org/W2069559626","https://openalex.org/W2070232376","https://openalex.org/W2072725684","https://openalex.org/W2079577430","https://openalex.org/W2084423328","https://openalex.org/W2096898433","https://openalex.org/W2102884673","https://openalex.org/W2108801243","https://openalex.org/W2117476908","https://openalex.org/W2119860027","https://openalex.org/W2129829929","https://openalex.org/W2130374657","https://openalex.org/W2131296084","https://openalex.org/W2136699870","https://openalex.org/W2146585781","https://openalex.org/W2155823485","https://openalex.org/W2166254818","https://openalex.org/W2171226522"],"related_works":["https://openalex.org/W3134625605","https://openalex.org/W2998925847","https://openalex.org/W2350803493","https://openalex.org/W2171195881","https://openalex.org/W2105141138","https://openalex.org/W1580674012","https://openalex.org/W2795285593","https://openalex.org/W1495085183","https://openalex.org/W2188995351","https://openalex.org/W1929987588"],"abstract_inverted_index":{"Modern":[0],"mainstream":[1],"powerful":[2],"computers":[3],"adopt":[4],"multisocket":[5],"multicore":[6],"CPU":[7],"architecture":[8],"and":[9,28,53,68,80,145,161,188],"NUMA-based":[10],"memory":[11,30,55,78,90,98],"architecture.":[12],"While":[13],"traditional":[14,166,198],"work-stealing":[15,43,137,167,199],"schedulers":[16],"are":[17,121],"designed":[18],"for":[19,95,129],"single-socket":[20],"architectures,":[21],"they":[22],"incur":[23],"severe":[24],"shared":[25,51,131],"cache":[26,52,132],"misses":[27],"remote":[29,97],"accesses":[31],"in":[32,148],"these":[33],"computers.":[34],"To":[35],"solve":[36],"the":[37,50,54,70,77,85,88,143,146,176],"problem,":[38],"we":[39,154],"propose":[40],"a":[41,59,73,82,135],"locality-aware":[42],"(LAWS)":[44],"scheduler,":[45],"which":[46],"better":[47],"utilizes":[48],"both":[49],"system.":[56],"In":[57],"LAWS,":[58],"load-balanced":[60],"task":[61,83],"allocator":[62],"is":[63,139],"used":[64],"to":[65,75,84,109,141,182,190],"evenly":[66],"split":[67],"store":[69],"dataset":[71],"of":[72,178],"program":[74],"all":[76],"nodes":[79],"allocate":[81],"socket":[86,124],"where":[87],"local":[89],"node":[91],"stores":[92],"its":[93],"data":[94],"reducing":[96],"accesses.":[99],"Then,":[100],"an":[101,106,112],"adaptive":[102],"DAG":[103,114],"packer":[104],"adopts":[105],"auto-tuning":[107],"approach":[108],"optimally":[110],"pack":[111],"execution":[113],"into":[115],"cache-friendly":[116,119,126],"subtrees.":[117],"After":[118],"subtrees":[120,127,144],"created,":[122],"every":[123],"executes":[125],"sequentially":[128],"optimizing":[130],"usage.":[133],"Meanwhile,":[134],"triple-level":[136],"scheduler":[138],"applied":[140],"schedule":[142],"tasks":[147],"each":[149],"subtree.":[150],"Through":[151],"theoretical":[152],"analysis,":[153],"show":[155,171],"that":[156,172],"LAWS":[157,173],"has":[158],"comparable":[159],"time":[160],"space":[162],"bounds":[163],"compared":[164,196],"with":[165,197],"schedulers.":[168,200],"Experimental":[169],"results":[170],"can":[174],"improve":[175],"performance":[177],"memory-bound":[179],"programs":[180],"up":[181,189],"54.2%":[183],"on":[184,192],"AMD-based":[185],"experimental":[186,194],"platforms":[187,195],"48.6%":[191],"Intel-based":[193]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":3}],"updated_date":"2026-04-16T08:26:57.006410","created_date":"2025-10-10T00:00:00"}
