{"id":"https://openalex.org/W3145135885","doi":"https://doi.org/10.1109/ipdps.2006.1639271","title":"Improving cache locality for thread-level speculation","display_name":"Improving cache locality for thread-level speculation","publication_year":2006,"publication_date":"2006-01-01","ids":{"openalex":"https://openalex.org/W3145135885","doi":"https://doi.org/10.1109/ipdps.2006.1639271","mag":"3145135885"},"language":"en","primary_location":{"id":"doi:10.1109/ipdps.2006.1639271","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdps.2006.1639271","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings 20th IEEE International Parallel & Distributed Processing Symposium","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/A5056108235","display_name":"Stanley L. C. Fung","orcid":null},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"S.L.C. Fung","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Toronto, Toronto, ONT, Canada"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Toronto, Toronto, ONT, Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110755517","display_name":"J. Gregory Steffan","orcid":null},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"J.G. Steffan","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Toronto, Toronto, ONT, Canada"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Toronto, Toronto, ONT, Canada","institution_ids":["https://openalex.org/I185261750"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5056108235"],"corresponding_institution_ids":["https://openalex.org/I185261750"],"apc_list":null,"apc_paid":null,"fwci":1.9867,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.87023289,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"6","issue":null,"first_page":"10 pp.","last_page":"10 pp."},"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9987000226974487,"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":0.9984999895095825,"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":0.86130690574646},{"id":"https://openalex.org/keywords/uniprocessor-system","display_name":"Uniprocessor system","score":0.8000302314758301},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.7381779551506042},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7378394603729248},{"id":"https://openalex.org/keywords/speculative-multithreading","display_name":"Speculative multithreading","score":0.7296763062477112},{"id":"https://openalex.org/keywords/cache-algorithms","display_name":"Cache algorithms","score":0.6683930158615112},{"id":"https://openalex.org/keywords/cache-invalidation","display_name":"Cache invalidation","score":0.6154876351356506},{"id":"https://openalex.org/keywords/bus-sniffing","display_name":"Bus sniffing","score":0.5899486541748047},{"id":"https://openalex.org/keywords/cache-coloring","display_name":"Cache coloring","score":0.5888625383377075},{"id":"https://openalex.org/keywords/cache-pollution","display_name":"Cache pollution","score":0.5859472751617432},{"id":"https://openalex.org/keywords/smart-cache","display_name":"Smart Cache","score":0.570871114730835},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.5654374361038208},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.530745267868042},{"id":"https://openalex.org/keywords/page-cache","display_name":"Page cache","score":0.47297611832618713},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.4321097433567047},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.4074837565422058},{"id":"https://openalex.org/keywords/cpu-cache","display_name":"CPU cache","score":0.40484151244163513},{"id":"https://openalex.org/keywords/multithreading","display_name":"Multithreading","score":0.3395555317401886},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3240787386894226},{"id":"https://openalex.org/keywords/multiprocessing","display_name":"Multiprocessing","score":0.07130670547485352}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.86130690574646},{"id":"https://openalex.org/C79189994","wikidata":"https://www.wikidata.org/wiki/Q3488021","display_name":"Uniprocessor system","level":3,"score":0.8000302314758301},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.7381779551506042},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7378394603729248},{"id":"https://openalex.org/C15296174","wikidata":"https://www.wikidata.org/wiki/Q7575343","display_name":"Speculative multithreading","level":4,"score":0.7296763062477112},{"id":"https://openalex.org/C38556500","wikidata":"https://www.wikidata.org/wiki/Q13404475","display_name":"Cache algorithms","level":4,"score":0.6683930158615112},{"id":"https://openalex.org/C25536678","wikidata":"https://www.wikidata.org/wiki/Q5015977","display_name":"Cache invalidation","level":5,"score":0.6154876351356506},{"id":"https://openalex.org/C51185590","wikidata":"https://www.wikidata.org/wiki/Q1017228","display_name":"Bus sniffing","level":5,"score":0.5899486541748047},{"id":"https://openalex.org/C201148951","wikidata":"https://www.wikidata.org/wiki/Q5015976","display_name":"Cache coloring","level":4,"score":0.5888625383377075},{"id":"https://openalex.org/C113166858","wikidata":"https://www.wikidata.org/wiki/Q5015981","display_name":"Cache pollution","level":5,"score":0.5859472751617432},{"id":"https://openalex.org/C167713795","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"Smart Cache","level":5,"score":0.570871114730835},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.5654374361038208},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.530745267868042},{"id":"https://openalex.org/C36340418","wikidata":"https://www.wikidata.org/wiki/Q7124288","display_name":"Page cache","level":5,"score":0.47297611832618713},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.4321097433567047},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.4074837565422058},{"id":"https://openalex.org/C189783530","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"CPU cache","level":3,"score":0.40484151244163513},{"id":"https://openalex.org/C201410400","wikidata":"https://www.wikidata.org/wiki/Q1064412","display_name":"Multithreading","level":3,"score":0.3395555317401886},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3240787386894226},{"id":"https://openalex.org/C4822641","wikidata":"https://www.wikidata.org/wiki/Q846651","display_name":"Multiprocessing","level":2,"score":0.07130670547485352},{"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:10.1109/ipdps.2006.1639271","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdps.2006.1639271","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings 20th IEEE International Parallel & Distributed Processing Symposium","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":18,"referenced_works":["https://openalex.org/W56414646","https://openalex.org/W1525227808","https://openalex.org/W2029479717","https://openalex.org/W2037462607","https://openalex.org/W2057074087","https://openalex.org/W2111905231","https://openalex.org/W2118383989","https://openalex.org/W2119609467","https://openalex.org/W2125305952","https://openalex.org/W2136798749","https://openalex.org/W2150547581","https://openalex.org/W2155010932","https://openalex.org/W2244841219","https://openalex.org/W3148387930","https://openalex.org/W4248446132","https://openalex.org/W4255238016","https://openalex.org/W6602309031","https://openalex.org/W6682926681"],"related_works":["https://openalex.org/W2133489088","https://openalex.org/W2155502730","https://openalex.org/W4237553843","https://openalex.org/W2088799683","https://openalex.org/W2154638254","https://openalex.org/W2130688751","https://openalex.org/W4249918808","https://openalex.org/W1980832712","https://openalex.org/W3145135885","https://openalex.org/W2110723369"],"abstract_inverted_index":{"With":[0],"the":[1,21,32,38,55,64,84,143],"advent":[2],"of":[3,23,63,109,145],"chip-multiprocessors":[4],"(CMPs),":[5],"thread-level":[6],"speculation":[7],"(TLS)":[8],"remains":[9],"a":[10,49,148],"promising":[11],"technique":[12],"for":[13,45,115],"exploiting":[14],"this":[15],"highly":[16],"multithreaded":[17],"hardware":[18],"to":[19,103,150],"improve":[20,104,132,138],"performance":[22,133],"an":[24],"individual":[25],"program.":[26],"However,":[27],"with":[28],"such":[29],"speculatively-parallel":[30],"execution":[31,41,47,70,94],"cache":[33,79,86,105],"locality":[34,87,106],"once":[35],"enjoyed":[36],"by":[37,130,134],"original":[39],"uniprocessor":[40,65],"is":[42],"significantly":[43,137],"disrupted:":[44],"TLS":[46,69,85,146],"on":[48,152],"four-processor":[50],"CMP,":[51],"we":[52],"find":[53,113],"that":[54,114],"data-cache":[56,128],"miss":[57],"rates":[58],"are":[59],"nearly":[60],"four-times":[61],"those":[62],"case,":[66],"even":[67],"though":[68],"utilizes":[71],"four":[72],"private":[73],"data":[74,92],"caches":[75],"(i.e.,":[76],"four-fold":[77],"greater":[78],"capacity).":[80],"We":[81,112],"break":[82],"down":[83],"problem":[88],"into":[89],"instruction":[90],"and":[91,96,100,124,136],"cache,":[93],"stages,":[95],"parallel":[97,116],"access":[98],"patterns,":[99],"propose":[101],"methods":[102],"in":[107],"each":[108],"these":[110],"areas.":[111],"regions":[117],"across":[118],"13":[119],"SPECint":[120],"applications":[121],"our":[122],"simple":[123],"low-cost":[125],"techniques":[126],"reduce":[127],"misses":[129],"38%,":[131],"12.8%,":[135],"scalability":[139],"-":[140],"further":[141],"enhancing":[142],"feasibility":[144],"as":[147],"way":[149],"capitalize":[151],"future":[153],"CMPs.":[154]},"counts_by_year":[{"year":2016,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}