{"id":"https://openalex.org/W2122892069","doi":"https://doi.org/10.1145/1183401.1183403","title":"A modern high-performance processor pipeline","display_name":"A modern high-performance processor pipeline","publication_year":2006,"publication_date":"2006-06-28","ids":{"openalex":"https://openalex.org/W2122892069","doi":"https://doi.org/10.1145/1183401.1183403","mag":"2122892069"},"language":"en","primary_location":{"id":"doi:10.1145/1183401.1183403","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1183401.1183403","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th annual international conference on Supercomputing","raw_type":"proceedings-article"},"type":"conference-abstract","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/A5109180969","display_name":"Marc Tremblay","orcid":null},"institutions":[{"id":"https://openalex.org/I1342911587","display_name":"Oracle (United States)","ror":"https://ror.org/006c77m33","country_code":"US","type":"company","lineage":["https://openalex.org/I1342911587"]},{"id":"https://openalex.org/I4210153877","display_name":"Microsystems (United Kingdom)","ror":"https://ror.org/04pvywd96","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210153877"]}],"countries":["GB","US"],"is_corresponding":true,"raw_author_name":"Marc Tremblay","raw_affiliation_strings":["Sun Microsystems, Inc","Sun Microsystems, Inc.#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Microsystems, Inc","institution_ids":["https://openalex.org/I4210153877"]},{"raw_affiliation_string":"Sun Microsystems, Inc.#TAB#","institution_ids":["https://openalex.org/I1342911587"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5109180969"],"corresponding_institution_ids":["https://openalex.org/I1342911587","https://openalex.org/I4210153877"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"1"},"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9983000159263611,"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":0.9965999722480774,"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":0.837682843208313},{"id":"https://openalex.org/keywords/microarchitecture","display_name":"Microarchitecture","score":0.5621335506439209},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.5608357191085815},{"id":"https://openalex.org/keywords/out-of-order-execution","display_name":"Out-of-order execution","score":0.5476263761520386},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5422656536102295},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5272454619407654},{"id":"https://openalex.org/keywords/multithreading","display_name":"Multithreading","score":0.5239757895469666},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.48313137888908386},{"id":"https://openalex.org/keywords/clock-rate","display_name":"Clock rate","score":0.4783563017845154},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.45632246136665344},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.43283534049987793},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.43195343017578125},{"id":"https://openalex.org/keywords/speculative-execution","display_name":"Speculative execution","score":0.4240458011627197},{"id":"https://openalex.org/keywords/speculative-multithreading","display_name":"Speculative multithreading","score":0.4130645990371704},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.37331366539001465},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.33931174874305725},{"id":"https://openalex.org/keywords/chip","display_name":"Chip","score":0.2892581820487976}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.837682843208313},{"id":"https://openalex.org/C107598950","wikidata":"https://www.wikidata.org/wiki/Q259864","display_name":"Microarchitecture","level":2,"score":0.5621335506439209},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.5608357191085815},{"id":"https://openalex.org/C1793878","wikidata":"https://www.wikidata.org/wiki/Q1153762","display_name":"Out-of-order execution","level":2,"score":0.5476263761520386},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5422656536102295},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5272454619407654},{"id":"https://openalex.org/C201410400","wikidata":"https://www.wikidata.org/wiki/Q1064412","display_name":"Multithreading","level":3,"score":0.5239757895469666},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.48313137888908386},{"id":"https://openalex.org/C178693496","wikidata":"https://www.wikidata.org/wiki/Q911691","display_name":"Clock rate","level":3,"score":0.4783563017845154},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.45632246136665344},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.43283534049987793},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.43195343017578125},{"id":"https://openalex.org/C141331961","wikidata":"https://www.wikidata.org/wiki/Q2164465","display_name":"Speculative execution","level":2,"score":0.4240458011627197},{"id":"https://openalex.org/C15296174","wikidata":"https://www.wikidata.org/wiki/Q7575343","display_name":"Speculative multithreading","level":4,"score":0.4130645990371704},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.37331366539001465},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.33931174874305725},{"id":"https://openalex.org/C165005293","wikidata":"https://www.wikidata.org/wiki/Q1074500","display_name":"Chip","level":2,"score":0.2892581820487976},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1183401.1183403","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1183401.1183403","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th annual international conference on Supercomputing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.5600000023841858}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2002219828","https://openalex.org/W2897302968","https://openalex.org/W4242936137","https://openalex.org/W2101113316","https://openalex.org/W2765149243","https://openalex.org/W4287754567","https://openalex.org/W3036933480","https://openalex.org/W1916582918","https://openalex.org/W2090754905","https://openalex.org/W2032573914"],"abstract_inverted_index":{"The":[0],"traditional":[1,49,56,135],"balance":[2],"between":[3],"processor":[4],"clock":[5],"rate":[6],"and":[7,19,55,76,123,129,173,211,215,233,239,252],"instruction":[8],"level":[9],"parallelism":[10],"(ILP)":[11],"has":[12],"been":[13],"severely":[14],"shaken":[15],"due":[16,71],"to":[17,63,72,87,161,268],"enablers":[18],"constraints":[20,118],"that":[21,167,198,255],"were":[22],"not":[23,27],"prevalent":[24],"or":[25],"did":[26],"exist":[28],"during":[29],"the":[30,35,78,179,187,225,257],"last":[31],"two":[32],"decades.":[33],"With":[34],"current":[36],"broad":[37,260],"deployment":[38],"of":[39,111,153,182,227,262],"multithreaded":[40,155],"software":[41],"for":[42,46,127],"servers":[43,267],"(increasing":[44],"rapidly":[45],"desktops),":[47],"a":[48,108,138,163,193,200,259],"processor,":[50],"e.g.":[51],"with":[52],"high":[53,170,174],"frequency":[54],"OoO":[57],"scheduling,":[58],"is":[59,82,90,178,186,221,243],"no":[60],"longer":[61],"optimal":[62],"extract":[64],"performance.":[65,116,176],"Moreover":[66],"as":[67,120],"cache":[68],"footprints":[69],"grow":[70],"problem":[73,81],"size,":[74],"scaling,":[75],"multiprogramming,":[77],"memory":[79],"wall":[80],"only":[83],"getting":[84],"worse.":[85],"Not":[86],"be":[88,205],"forgotten":[89],"Amdahl's":[91],"law,":[92],"which":[93],"in":[94,192,247],"this":[95],"context":[96],"of,":[97],"on-chip":[98],"closely-coupled":[99],"parallel":[100],"execution,":[101],"makes":[102],"single-thread":[103,175],"performance":[104,172],"important":[105],"since":[106],"even":[107],"small":[109,266],"fraction":[110],"non-scalable":[112],"code":[113],"affects":[114],"overall":[115,124],"Other":[117],"such":[119],"power":[121,125],"density":[122],"limitation":[126],"air-":[128],"liquid-cooled":[130],"systems":[131,263],"make":[132],"putting":[133],"multiple":[134,154,245],"cores":[136],"on":[137],"single":[139],"die":[140],"an":[141,158],"unattractive":[142],"design":[143],"point.":[144],"High-Performance":[145],"Throughput":[146],"Computing,":[147],"achieved":[148],"through":[149,230,236],"design-from-scratch":[150],"processors":[151,254],"composed":[152],"cores,":[156],"offers":[157,199],"unprecedented":[159],"opportunity":[160],"create":[162],"new":[164,190,201],"generation":[165],"pipeline":[166,191,228,242],"delivers":[168],"both":[169],"throughput":[171],"This":[177,241],"first":[180,188],"disclosure":[181],"what":[183],"we":[184],"believe":[185],"truly":[189],"decade.":[194],"A":[195],"checkpoint-based":[196],"architecture":[197],"execution":[202],"model":[203],"will":[204],"described.":[206],"Hardware":[207],"threads":[208],"are":[209],"spawned":[210],"they":[212],"speculatively":[213],"execute":[214],"retire":[216],"instructions":[217],"out-of-order.":[218],"Power":[219],"efficiency":[220],"emphasized":[222],"by":[223],"maximizing":[224],"utilization":[226],"stages":[229],"temporal":[231],"threading":[232,238],"functional":[234],"units":[235],"spatial":[237],"speculation.":[240],"embedded":[244],"times":[246],"our":[248],"future":[249],"high-end":[250],"65nm":[251],"45nm":[253],"form":[256],"cornerstone":[258],"line":[261],"ranging":[264],"from":[265],"supercomputers.":[269]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}