{"id":"https://openalex.org/W2257827631","doi":"https://doi.org/10.1145/2851141.2851194","title":"Affinity-aware work-stealing for integrated CPU-GPU processors","display_name":"Affinity-aware work-stealing for integrated CPU-GPU processors","publication_year":2016,"publication_date":"2016-02-22","ids":{"openalex":"https://openalex.org/W2257827631","doi":"https://doi.org/10.1145/2851141.2851194","mag":"2257827631"},"language":"en","primary_location":{"id":"doi:10.1145/2851141.2851194","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2851141.2851194","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming","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/A5055965833","display_name":"Naila Farooqui","orcid":"https://orcid.org/0000-0001-6592-5328"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Naila Farooqui","raw_affiliation_strings":["Georgia Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108643447","display_name":"Rajkishore Barik","orcid":null},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rajkishore Barik","raw_affiliation_strings":["Intel Labs"],"affiliations":[{"raw_affiliation_string":"Intel Labs","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111709219","display_name":"Brian T. R. Lewis","orcid":null},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brian T. Lewis","raw_affiliation_strings":["Intel Labs"],"affiliations":[{"raw_affiliation_string":"Intel Labs","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076969648","display_name":"Tatiana Shpeisman","orcid":"https://orcid.org/0000-0002-4225-8734"},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tatiana Shpeisman","raw_affiliation_strings":["Intel Labs"],"affiliations":[{"raw_affiliation_string":"Intel Labs","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111483107","display_name":"Karsten Schwan","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Karsten Schwan","raw_affiliation_strings":["Georgia Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5055965833"],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":null,"apc_paid":null,"fwci":0.946,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.71788603,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"2"},"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/T10829","display_name":"Interconnection Networks and 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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9994000196456909,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8452391624450684},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6832300424575806},{"id":"https://openalex.org/keywords/cpu-shielding","display_name":"CPU shielding","score":0.61811363697052},{"id":"https://openalex.org/keywords/central-processing-unit","display_name":"Central processing unit","score":0.5863491296768188},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.5299053192138672},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.4848681390285492},{"id":"https://openalex.org/keywords/cpu-cache","display_name":"CPU cache","score":0.46736881136894226},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.4446752071380615},{"id":"https://openalex.org/keywords/instruction-set","display_name":"Instruction set","score":0.4378831386566162},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.43279415369033813},{"id":"https://openalex.org/keywords/memory-management","display_name":"Memory management","score":0.4118845462799072},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.35113635659217834},{"id":"https://openalex.org/keywords/semiconductor-memory","display_name":"Semiconductor memory","score":0.07441112399101257}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8452391624450684},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6832300424575806},{"id":"https://openalex.org/C180613757","wikidata":"https://www.wikidata.org/wiki/Q5013757","display_name":"CPU shielding","level":3,"score":0.61811363697052},{"id":"https://openalex.org/C49154492","wikidata":"https://www.wikidata.org/wiki/Q5300","display_name":"Central processing unit","level":2,"score":0.5863491296768188},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.5299053192138672},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.4848681390285492},{"id":"https://openalex.org/C189783530","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"CPU cache","level":3,"score":0.46736881136894226},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.4446752071380615},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.4378831386566162},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.43279415369033813},{"id":"https://openalex.org/C176649486","wikidata":"https://www.wikidata.org/wiki/Q2308807","display_name":"Memory management","level":3,"score":0.4118845462799072},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.35113635659217834},{"id":"https://openalex.org/C98986596","wikidata":"https://www.wikidata.org/wiki/Q1143031","display_name":"Semiconductor memory","level":2,"score":0.07441112399101257}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2851141.2851194","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2851141.2851194","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W1966344015","https://openalex.org/W2016559894","https://openalex.org/W2121893797","https://openalex.org/W2150476673","https://openalex.org/W2157124218","https://openalex.org/W2159952265","https://openalex.org/W2169049902"],"related_works":["https://openalex.org/W2387982802","https://openalex.org/W1896942098","https://openalex.org/W1991061790","https://openalex.org/W2088078730","https://openalex.org/W2400763249","https://openalex.org/W1502438194","https://openalex.org/W2254409681","https://openalex.org/W2368611950","https://openalex.org/W2803934143","https://openalex.org/W2033171136"],"abstract_inverted_index":{"Recent":[0],"integrated":[1,80],"CPU-GPU":[2,12,24,81],"processors":[3],"like":[4],"Intel's":[5],"Broadwell":[6,111],"and":[7,18,32,53,55,104],"AMD's":[8],"Kaveri":[9],"support":[10],"hardware":[11],"shared":[13,56],"virtual":[14],"memory,":[15],"atomic":[16,50],"operations,":[17],"memory":[19,57],"coherency.":[20],"This":[21,59],"enables":[22],"fine-grained":[23],"work-stealing,":[25,125],"but":[26],"architectural":[27,44,77],"differences":[28,45,78],"between":[29],"the":[30,35],"CPU":[31],"GPU":[33],"hurt":[34],"performance":[36,88,121],"of":[37,65,101],"traditionally-implemented":[38],"work-stealing":[39,67],"on":[40,108],"such":[41],"processors.":[42,82],"These":[43],"include":[46],"different":[47],"clock":[48],"frequencies,":[49],"operation":[51],"costs,":[52],"cache":[54],"latencies.":[58],"paper":[60],"describes":[61],"a":[62,98,119,127],"preliminary":[63,95],"implementation":[64],"our":[66],"scheduler,":[68],"Libra,":[69],"which":[70],"includes":[71],"techniques":[72,85],"to":[73,118],"deal":[74],"with":[75,126],"these":[76],"in":[79],"Libra's":[83],"affinity-aware":[84],"achieve":[86],"significant":[87],"gains":[89],"over":[90,123],"classically-implemented":[91],"work-stealing.":[92],"We":[93],"show":[94],"results":[96],"using":[97],"diverse":[99],"set":[100],"nine":[102],"regular":[103],"irregular":[105],"workloads":[106],"running":[107],"an":[109],"Intel":[110],"Core-M":[112],"processor.":[113],"Libra":[114],"currently":[115],"achieves":[116],"up":[117],"2\u00d7":[120],"improvement":[122],"classical":[124],"20%":[128],"average":[129],"improvement.":[130]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}