{"id":"https://openalex.org/W4240436476","doi":"https://doi.org/10.1109/cgo.2004.1281661","title":"Physical experimentation with prefetching helper threads on Intel's hyper-threaded processors","display_name":"Physical experimentation with prefetching helper threads on Intel's hyper-threaded processors","publication_year":2004,"publication_date":"2004-06-10","ids":{"openalex":"https://openalex.org/W4240436476","doi":"https://doi.org/10.1109/cgo.2004.1281661"},"language":"en","primary_location":{"id":"doi:10.1109/cgo.2004.1281661","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cgo.2004.1281661","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Symposium on Code Generation and Optimization, 2004. CGO 2004.","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/A5111529492","display_name":"Dong-Keun Kim","orcid":"https://orcid.org/0000-0001-6093-126X"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Dongkeun Kim","raw_affiliation_strings":["Department of ECE, Institute for Advanced Computer Studies, University of Maryland College Park, USA"],"affiliations":[{"raw_affiliation_string":"Department of ECE, Institute for Advanced Computer Studies, University of Maryland College Park, USA","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072040648","display_name":"S.S. Liao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"S.S. Liao","raw_affiliation_strings":["Microarchitecture Research Laboratory"],"affiliations":[{"raw_affiliation_string":"Microarchitecture Research Laboratory","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061815420","display_name":"P.H. Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"P.H. Wang","raw_affiliation_strings":["Microarchitecture Research Laboratory"],"affiliations":[{"raw_affiliation_string":"Microarchitecture Research Laboratory","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060061661","display_name":"Juan del Cuvillo","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":"J. del Cuvillo","raw_affiliation_strings":["Intel Compiler Laboratories, Intel Corporation, USA"],"affiliations":[{"raw_affiliation_string":"Intel Compiler Laboratories, Intel Corporation, USA","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101131112","display_name":"Xinmin Tian","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":"Xinmin Tian","raw_affiliation_strings":["Intel Compiler Laboratories, Intel Corporation, USA"],"affiliations":[{"raw_affiliation_string":"Intel Compiler Laboratories, Intel Corporation, USA","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100570474","display_name":"Xiang Zou","orcid":"https://orcid.org/0009-0004-6461-2660"},"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":"Xiang Zou","raw_affiliation_strings":["Desktop Platforms Group, Intel Corporation, USA"],"affiliations":[{"raw_affiliation_string":"Desktop Platforms Group, Intel Corporation, USA","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100371015","display_name":"Hong Wang","orcid":"https://orcid.org/0009-0008-2874-2168"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hong Wang","raw_affiliation_strings":["Microarchitecture Research Laboratory"],"affiliations":[{"raw_affiliation_string":"Microarchitecture Research Laboratory","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042239243","display_name":"Donald Yeung","orcid":"https://orcid.org/0000-0003-0341-2644"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"D. Yeung","raw_affiliation_strings":["Department of ECE, Institute for Advanced Computer Studies, University of Maryland College Park, USA"],"affiliations":[{"raw_affiliation_string":"Department of ECE, Institute for Advanced Computer Studies, University of Maryland College Park, USA","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009108433","display_name":"Milind Girkar","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":"M. Girkar","raw_affiliation_strings":["Intel Compiler Laboratories, Intel Corporation, USA"],"affiliations":[{"raw_affiliation_string":"Intel Compiler Laboratories, Intel Corporation, USA","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019940127","display_name":"J.P. Shen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"J.P. Shen","raw_affiliation_strings":["Microarchitecture Research Laboratory"],"affiliations":[{"raw_affiliation_string":"Microarchitecture Research Laboratory","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5111529492"],"corresponding_institution_ids":["https://openalex.org/I66946132"],"apc_list":null,"apc_paid":null,"fwci":1.5798,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.83779199,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"27","last_page":"38"},"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/T11005","display_name":"Radiation Effects in Electronics","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10904","display_name":"Embedded Systems Design Techniques","score":0.9984999895095825,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8848761320114136},{"id":"https://openalex.org/keywords/multithreading","display_name":"Multithreading","score":0.8110562562942505},{"id":"https://openalex.org/keywords/simultaneous-multithreading","display_name":"Simultaneous multithreading","score":0.7504727840423584},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.7445827126502991},{"id":"https://openalex.org/keywords/speculative-multithreading","display_name":"Speculative multithreading","score":0.6263474225997925},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6076163053512573},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.5940718650817871},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.5652399063110352},{"id":"https://openalex.org/keywords/yarn","display_name":"Yarn","score":0.5010402202606201},{"id":"https://openalex.org/keywords/pentium","display_name":"Pentium","score":0.43807563185691833},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.4127857983112335},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3649722933769226},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.3491906523704529}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8848761320114136},{"id":"https://openalex.org/C201410400","wikidata":"https://www.wikidata.org/wiki/Q1064412","display_name":"Multithreading","level":3,"score":0.8110562562942505},{"id":"https://openalex.org/C85717602","wikidata":"https://www.wikidata.org/wiki/Q82178","display_name":"Simultaneous multithreading","level":4,"score":0.7504727840423584},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.7445827126502991},{"id":"https://openalex.org/C15296174","wikidata":"https://www.wikidata.org/wiki/Q7575343","display_name":"Speculative multithreading","level":4,"score":0.6263474225997925},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6076163053512573},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.5940718650817871},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.5652399063110352},{"id":"https://openalex.org/C2778787235","wikidata":"https://www.wikidata.org/wiki/Q49007","display_name":"Yarn","level":2,"score":0.5010402202606201},{"id":"https://openalex.org/C46268123","wikidata":"https://www.wikidata.org/wiki/Q214314","display_name":"Pentium","level":2,"score":0.43807563185691833},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.4127857983112335},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3649722933769226},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3491906523704529},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cgo.2004.1281661","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cgo.2004.1281661","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Symposium on Code Generation and Optimization, 2004. CGO 2004.","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.6000000238418579}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W4424585","https://openalex.org/W63944998","https://openalex.org/W1539430313","https://openalex.org/W1542121714","https://openalex.org/W2043613230","https://openalex.org/W2044773873","https://openalex.org/W2111905231","https://openalex.org/W2125305952","https://openalex.org/W2126605567","https://openalex.org/W2160401437","https://openalex.org/W2168214303","https://openalex.org/W2170582961","https://openalex.org/W2249344705","https://openalex.org/W2293624369","https://openalex.org/W4230657362","https://openalex.org/W4240535691","https://openalex.org/W4242484660","https://openalex.org/W4244072202","https://openalex.org/W4247951052","https://openalex.org/W4251329058","https://openalex.org/W6602613798","https://openalex.org/W6632220093","https://openalex.org/W6691343681","https://openalex.org/W6694559567"],"related_works":["https://openalex.org/W2115561485","https://openalex.org/W1985089255","https://openalex.org/W4237941914","https://openalex.org/W1541942136","https://openalex.org/W1976136846","https://openalex.org/W94981340","https://openalex.org/W2003413578","https://openalex.org/W2621634031","https://openalex.org/W2171607039","https://openalex.org/W2153202644"],"abstract_inverted_index":{"Pre-execution":[0],"techniques":[1,24],"have":[2,31],"received":[3],"much":[4],"attention":[5],"as":[6],"an":[7],"effective":[8],"way":[9],"of":[10,22,131],"prefetching":[11],"cache":[12],"blocks":[13],"to":[14,163,170,184,190],"tolerate":[15],"the":[16,54,129,137,146,151,171,191],"ever-increasing":[17],"memory":[18],"latency.":[19],"A":[20],"number":[21],"pre-execution":[23],"based":[25],"on":[26,43,58,80],"hardware,":[27],"compiler,":[28],"or":[29,143],"both":[30],"been":[32],"proposed":[33],"and":[34,71,104,109,114,149],"studied":[35],"extensively":[36],"by":[37,100,168],"researchers.":[38],"They":[39],"report":[40],"promising":[41],"results":[42],"simulators":[44],"that":[45,73,97,176],"model":[46],"a":[47,59,120],"simultaneous":[48],"multithreading":[49,147],"(SMT)":[50],"processor.":[51],"We":[52],"apply":[53],"helper":[55,89,94,166],"threading":[56,95],"idea":[57],"real":[60,81],"multithreaded":[61],"machine,":[62],"i.e.,":[63],"Intel":[64],"Pentium":[65],"4":[66],"processor":[67],"with":[68],"hyper-threading":[69],"technology,":[70],"show":[72],"indeed":[74],"it":[75,160],"can":[76,156,178],"provide":[77],"wall-clock":[78],"speedup":[79],"silicon.":[82],"To":[83],"achieve":[84],"further":[85],"performance":[86,181],"improvements":[87],"via":[88],"threads,":[90],"we":[91,177],"investigate":[92],"three":[93],"scenarios":[96],"are":[98,140],"driven":[99],"automated":[101],"compiler":[102],"infrastructure,":[103],"identify":[105],"several":[106],"key":[107],"challenges":[108],"opportunities":[110],"for":[111],"novel":[112],"hardware":[113,134],"software":[115],"optimizations.":[116],"Our":[117],"study":[118],"shows":[119],"program":[121,173],"behavior":[122,174,193],"changes":[123],"dynamically":[124],"during":[125],"execution.":[126],"In":[127],"addition,":[128],"organizations":[130],"certain":[132],"critical":[133],"structures":[135],"in":[136,145],"hyper-threaded":[138],"processors":[139],"either":[141],"shared":[142],"partitioned":[144],"mode":[148],"thus,":[150],"tradeoffs":[152],"regarding":[153],"resource":[154,185],"contention":[155],"be":[157],"intricate.":[158],"Therefore,":[159],"is":[161,203],"essential":[162],"judiciously":[164],"invoke":[165],"threads":[167],"adapting":[169,189],"dynamic":[172,192],"so":[175],"alleviate":[179],"potential":[180],"degradation":[182],"due":[183],"contention.":[186],"Moreover,":[187],"since":[188],"requires":[194],"frequent":[195],"thread":[196,200],"synchronization,":[197],"having":[198],"light-weight":[199],"synchronization":[201],"mechanisms":[202],"important.":[204]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}