{"id":"https://openalex.org/W2125212667","doi":"https://doi.org/10.1145/1504176.1504208","title":"A compiler-directed data prefetching scheme for chip multiprocessors","display_name":"A compiler-directed data prefetching scheme for chip multiprocessors","publication_year":2009,"publication_date":"2009-02-14","ids":{"openalex":"https://openalex.org/W2125212667","doi":"https://doi.org/10.1145/1504176.1504208","mag":"2125212667"},"language":"en","primary_location":{"id":"doi:10.1145/1504176.1504208","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1504176.1504208","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th 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/A5102805559","display_name":"Seung Woo Son","orcid":"https://orcid.org/0000-0001-8922-418X"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Seung Woo Son","raw_affiliation_strings":["Pennsylvania State University, University Park, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pennsylvania State University, University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007116603","display_name":"Mahmut Kandemir","orcid":"https://orcid.org/0000-0002-9940-9951"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mahmut Kandemir","raw_affiliation_strings":["Pennsylvania State University, University Park, PA, Macao"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pennsylvania State University, University Park, PA, Macao","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077359864","display_name":"Mustafa Karak\u00f6y","orcid":"https://orcid.org/0000-0001-7499-0834"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mustafa Karakoy","raw_affiliation_strings":["Imperial College, London, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College, London, United Kingdom","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038499695","display_name":"Dhruva R. Chakrabarti","orcid":"https://orcid.org/0009-0008-4660-7584"},"institutions":[{"id":"https://openalex.org/I1324840837","display_name":"Hewlett-Packard (United States)","ror":"https://ror.org/059rn9488","country_code":"US","type":"company","lineage":["https://openalex.org/I1324840837"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dhruva Chakrabarti","raw_affiliation_strings":["HP Labs, Cupertino, CA, USA","HP Labs, Cupertino, CA, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HP Labs, Cupertino, CA, USA","institution_ids":["https://openalex.org/I1324840837"]},{"raw_affiliation_string":"HP Labs, Cupertino, CA, USA#TAB#","institution_ids":["https://openalex.org/I1324840837"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.6809,"has_fulltext":false,"cited_by_count":38,"citation_normalized_percentile":{"value":0.90688872,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"209","last_page":"218"},"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9998999834060669,"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/T10772","display_name":"Distributed systems and fault tolerance","score":0.9954000115394592,"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/instruction-prefetch","display_name":"Instruction prefetch","score":0.9380104541778564},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8645226359367371},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7803667783737183},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.6574368476867676},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6189444065093994},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.5832833051681519},{"id":"https://openalex.org/keywords/spec#","display_name":"Spec#","score":0.5130363702774048},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.48395827412605286},{"id":"https://openalex.org/keywords/cas-latency","display_name":"CAS latency","score":0.47721678018569946},{"id":"https://openalex.org/keywords/cpu-cache","display_name":"CPU cache","score":0.4227983355522156},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.29953086376190186},{"id":"https://openalex.org/keywords/memory-controller","display_name":"Memory controller","score":0.09803026914596558}],"concepts":[{"id":"https://openalex.org/C133588205","wikidata":"https://www.wikidata.org/wiki/Q28455645","display_name":"Instruction prefetch","level":3,"score":0.9380104541778564},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8645226359367371},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7803667783737183},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.6574368476867676},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6189444065093994},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.5832833051681519},{"id":"https://openalex.org/C2778565505","wikidata":"https://www.wikidata.org/wiki/Q2207566","display_name":"Spec#","level":2,"score":0.5130363702774048},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.48395827412605286},{"id":"https://openalex.org/C189930140","wikidata":"https://www.wikidata.org/wiki/Q1112878","display_name":"CAS latency","level":4,"score":0.47721678018569946},{"id":"https://openalex.org/C189783530","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"CPU cache","level":3,"score":0.4227983355522156},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.29953086376190186},{"id":"https://openalex.org/C100800780","wikidata":"https://www.wikidata.org/wiki/Q1175867","display_name":"Memory controller","level":3,"score":0.09803026914596558},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C98986596","wikidata":"https://www.wikidata.org/wiki/Q1143031","display_name":"Semiconductor memory","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1504176.1504208","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1504176.1504208","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th 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":56,"referenced_works":["https://openalex.org/W148895426","https://openalex.org/W1571028795","https://openalex.org/W1936365067","https://openalex.org/W1971851724","https://openalex.org/W1976623675","https://openalex.org/W1979890365","https://openalex.org/W2016558956","https://openalex.org/W2016842024","https://openalex.org/W2021065197","https://openalex.org/W2022740893","https://openalex.org/W2024043936","https://openalex.org/W2025597060","https://openalex.org/W2057074087","https://openalex.org/W2072737419","https://openalex.org/W2076252126","https://openalex.org/W2086697860","https://openalex.org/W2097385643","https://openalex.org/W2099958604","https://openalex.org/W2101587002","https://openalex.org/W2102532014","https://openalex.org/W2109850171","https://openalex.org/W2109915751","https://openalex.org/W2111905231","https://openalex.org/W2112482891","https://openalex.org/W2116192839","https://openalex.org/W2118898690","https://openalex.org/W2119609467","https://openalex.org/W2120274141","https://openalex.org/W2120635877","https://openalex.org/W2122418911","https://openalex.org/W2126605567","https://openalex.org/W2136276584","https://openalex.org/W2138677746","https://openalex.org/W2139970538","https://openalex.org/W2140460036","https://openalex.org/W2143345821","https://openalex.org/W2145118374","https://openalex.org/W2147403610","https://openalex.org/W2148589677","https://openalex.org/W2148954445","https://openalex.org/W2150864656","https://openalex.org/W2151679317","https://openalex.org/W2153515302","https://openalex.org/W2154702295","https://openalex.org/W2154761638","https://openalex.org/W2155119470","https://openalex.org/W2155168119","https://openalex.org/W2161578546","https://openalex.org/W2167345029","https://openalex.org/W2170282806","https://openalex.org/W4231002400","https://openalex.org/W4241850174","https://openalex.org/W4251328264","https://openalex.org/W6676870935","https://openalex.org/W6755879534","https://openalex.org/W6864487941"],"related_works":["https://openalex.org/W2133197087","https://openalex.org/W1530597339","https://openalex.org/W2336226224","https://openalex.org/W134340165","https://openalex.org/W2068131691","https://openalex.org/W1557286738","https://openalex.org/W2546695182","https://openalex.org/W2101018784","https://openalex.org/W3113336200","https://openalex.org/W1578001114"],"abstract_inverted_index":{"Data":[0],"prefetching":[1,19,54,71,123,194,233,268],"has":[2],"been":[3],"widely":[4],"used":[5],"in":[6,20,58,74],"the":[7,49,84,103,145,169,181,203,206,213,224,230,260,266,274,291],"past":[8],"as":[9,83,100],"a":[10,36,110,120,154,195,280],"technique":[11],"for":[12,35,106,125,198],"hiding":[13],"memory":[14],"access":[15],"latencies.":[16],"However,":[17],"data":[18,53,62,70,122,187,232,240],"multi-threaded":[21,65],"applications":[22,66,204],"running":[23],"on":[24,55,180,242],"chip":[25],"multiprocessors":[26],"(CMPs)":[27],"can":[28,301],"be":[29,302],"problematic":[30],"when":[31,244],"multiple":[32],"cores":[33,87,246,256],"compete":[34],"shared":[37,56,126,182],"on-chip":[38,127],"cache":[39,128,183],"(L2":[40],"or":[41],"L3).":[42],"In":[43],"this":[44],"paper,":[45],"we":[46],"(i)":[47],"quantify":[48],"impact":[50],"of":[51,77,86,102,113,163,172,283,285],"conventional":[52,231,267],"caches":[57],"CMPs.":[59,130,199],"The":[60,131,249],"experimental":[61],"collected":[63],"using":[64,138,304],"indicates":[67],"that,":[68],"while":[69],"improves":[72,216],"performance":[73,108,252],"small":[75],"number":[76,85,112,171],"cores,":[78],"its":[79,239],"benefits":[80],"reduce":[81,168],"significantly":[82],"is":[88,93,277],"increased,":[89],"that":[90,212,273,300],"is,":[91],"it":[92,293],"not":[94],"scalable;":[95],"(ii)":[96],"identify":[97],"harmful":[98],"prefetches":[99,173,238],"one":[101],"main":[104],"contributors":[105],"degraded":[107],"with":[109,202,254],"large":[111],"cores;":[114],"and":[115,118,142,152,177,189,227,263,290],"(iii)":[116],"propose":[117],"evaluate":[119],"compiler-directed":[121,193],"scheme":[124,133,215,234,276],"based":[129],"proposed":[132,214,275],"first":[134],"identifies":[135],"program":[136],"phases":[137],"static":[139],"compiler":[140],"analysis,":[141],"then":[143],"divides":[144],"threads":[146],"into":[147],"groups":[148],"within":[149],"each":[150,161,236],"phase":[151],"assigns":[153],"customized":[155],"prefetcher":[156],"thread":[157],"(helper":[158],"thread)":[159],"to":[160,167,186,298],"group":[162],"threads.":[164],"This":[165],"helps":[166],"total":[170],"issued,":[174],"prefetch":[175],"overheads,":[176],"negative":[178],"interactions":[179],"space":[184],"due":[185],"prefetches,":[188],"more":[190],"importantly,":[191],"makes":[192],"scalable":[196],"optimization":[197],"Our":[200],"experiments":[201],"from":[205],"SPEC":[207],"OMP":[208],"benchmark":[209],"suite":[210],"indicate":[211],"overall":[217],"parallel":[218],"execution":[219],"latency":[220],"by":[221],"18.3%":[222],"over":[223,229],"no-prefetch":[225,261],"case":[226],"6.4%":[228],"(where":[235],"core":[237],"independently),":[241],"average,":[243],"12":[245],"are":[247,257],"used.":[248],"corresponding":[250],"average":[251],"improvements":[253,292],"24":[255],"16.4%":[258],"(over":[259,265],"case)":[262],"11.7%":[264],"case).":[269],"We":[270],"also":[271],"demonstrate":[272],"robust":[278],"under":[279],"wide":[281],"range":[282],"values":[284],"our":[286],"major":[287],"simulation":[288],"parameters,":[289],"achieves":[294],"come":[295],"very":[296],"close":[297],"those":[299],"achieved":[303],"an":[305],"optimal":[306],"scheme.":[307]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":12},{"year":2012,"cited_by_count":5}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}