{"id":"https://openalex.org/W2079746183","doi":"https://doi.org/10.1145/2579675","title":"Tuning the continual flow pipeline architecture with virtual register renaming","display_name":"Tuning the continual flow pipeline architecture with virtual register renaming","publication_year":2014,"publication_date":"2014-02-01","ids":{"openalex":"https://openalex.org/W2079746183","doi":"https://doi.org/10.1145/2579675","mag":"2079746183"},"language":"en","primary_location":{"id":"doi:10.1145/2579675","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2579675","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/2579675","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/2579675","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5025989918","display_name":"Komal Jothi","orcid":null},"institutions":[{"id":"https://openalex.org/I98635879","display_name":"American University of Beirut","ror":"https://ror.org/04pznsd21","country_code":"LB","type":"education","lineage":["https://openalex.org/I98635879"]}],"countries":["LB"],"is_corresponding":true,"raw_author_name":"Komal Jothi","raw_affiliation_strings":["American University of Beirut, Lebanon","American University of Beirut , Lebanon"],"affiliations":[{"raw_affiliation_string":"American University of Beirut, Lebanon","institution_ids":["https://openalex.org/I98635879"]},{"raw_affiliation_string":"American University of Beirut , Lebanon","institution_ids":["https://openalex.org/I98635879"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065922595","display_name":"Haitham Akkary","orcid":null},"institutions":[{"id":"https://openalex.org/I98635879","display_name":"American University of Beirut","ror":"https://ror.org/04pznsd21","country_code":"LB","type":"education","lineage":["https://openalex.org/I98635879"]}],"countries":["LB"],"is_corresponding":false,"raw_author_name":"Haitham Akkary","raw_affiliation_strings":["American University of Beirut, Lebanon","American University of Beirut , Lebanon"],"affiliations":[{"raw_affiliation_string":"American University of Beirut, Lebanon","institution_ids":["https://openalex.org/I98635879"]},{"raw_affiliation_string":"American University of Beirut , Lebanon","institution_ids":["https://openalex.org/I98635879"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5025989918"],"corresponding_institution_ids":["https://openalex.org/I98635879"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.13491219,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"11","issue":"1","first_page":"1","last_page":"27"},"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":0.9988999962806702,"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/T11181","display_name":"Advanced Data Storage Technologies","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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.9198787808418274},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.7099261283874512},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.7037367820739746},{"id":"https://openalex.org/keywords/microarchitecture","display_name":"Microarchitecture","score":0.6296318173408508},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5121895670890808},{"id":"https://openalex.org/keywords/processor-register","display_name":"Processor register","score":0.5005519390106201},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4499264657497406},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.4447604715824127},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.4433372914791107},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.38102632761001587},{"id":"https://openalex.org/keywords/memory-address","display_name":"Memory address","score":0.10385516285896301}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9198787808418274},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7099261283874512},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.7037367820739746},{"id":"https://openalex.org/C107598950","wikidata":"https://www.wikidata.org/wiki/Q259864","display_name":"Microarchitecture","level":2,"score":0.6296318173408508},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5121895670890808},{"id":"https://openalex.org/C2871975","wikidata":"https://www.wikidata.org/wiki/Q187466","display_name":"Processor register","level":4,"score":0.5005519390106201},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4499264657497406},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.4447604715824127},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.4433372914791107},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.38102632761001587},{"id":"https://openalex.org/C153247305","wikidata":"https://www.wikidata.org/wiki/Q835713","display_name":"Memory address","level":3,"score":0.10385516285896301},{"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:10.1145/2579675","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2579675","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/2579675","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/2579675","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2579675","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/2579675","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.9100000262260437,"id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2079746183.pdf","grobid_xml":"https://content.openalex.org/works/W2079746183.grobid-xml"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W37820266","https://openalex.org/W1868432933","https://openalex.org/W1975371390","https://openalex.org/W2013129990","https://openalex.org/W2019674193","https://openalex.org/W2026837239","https://openalex.org/W2033785728","https://openalex.org/W2034996068","https://openalex.org/W2064909421","https://openalex.org/W2071568619","https://openalex.org/W2077398506","https://openalex.org/W2096234108","https://openalex.org/W2099786221","https://openalex.org/W2102081731","https://openalex.org/W2102727118","https://openalex.org/W2105255467","https://openalex.org/W2108039095","https://openalex.org/W2112323430","https://openalex.org/W2113009671","https://openalex.org/W2118859527","https://openalex.org/W2118896605","https://openalex.org/W2120230074","https://openalex.org/W2120628323","https://openalex.org/W2123608497","https://openalex.org/W2137953999","https://openalex.org/W2141165425","https://openalex.org/W2145148711","https://openalex.org/W2148004594","https://openalex.org/W2149379863","https://openalex.org/W2151345470","https://openalex.org/W2167100385","https://openalex.org/W2170585292","https://openalex.org/W2542426564","https://openalex.org/W4232096869","https://openalex.org/W4245851057","https://openalex.org/W4250884001","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2005635288","https://openalex.org/W2081416538","https://openalex.org/W2131429702","https://openalex.org/W2540018280","https://openalex.org/W2141799201","https://openalex.org/W2111412181","https://openalex.org/W2101005180","https://openalex.org/W4251089459","https://openalex.org/W2115138121","https://openalex.org/W2169029159"],"abstract_inverted_index":{"Continual":[0],"Flow":[1],"Pipelines":[2],"(CFPs)":[3],"allow":[4],"a":[5,20,39,175,252],"processor":[6,29,54],"core":[7],"to":[8,42,85,119,125,153,187,193,251],"process":[9],"hundreds":[10],"of":[11,95,115,144,149,214],"in-flight":[12],"instructions":[13,37,48,65,105,111],"without":[14],"increasing":[15],"cycle-critical":[16],"pipeline":[17,100],"resources.":[18],"When":[19,56],"load":[21],"misses":[22,84,129],"the":[23,28,44,53,57,63,67,72,92,99,132,154,170,184,194],"data":[24,59,127],"cache,":[25],"CFP":[26,61,78,96,124,161,171,228,259],"checkpoints":[27],"register":[30,178],"state":[31],"and":[32,51,69,74,106,109,162,181,191,202,208,211,223,232],"then":[33,70],"moves":[34],"all":[35],"miss-dependent":[36,64,73,104],"into":[38],"low-complexity":[40],"WB":[41,68],"unblock":[43],"pipeline.":[45],"Meanwhile,":[46],"miss-independent":[47,75],"execute":[49],"normally":[50],"update":[52],"state.":[55],"miss":[58],"return,":[60],"replays":[62,190],"from":[66,160],"merges":[71],"execution":[76,93,142],"results.":[77],"was":[79,118],"initially":[80],"proposed":[81,240],"for":[82],"cache":[83,128],"DRAM.":[86],"Later":[87],"work":[88],"focused":[89],"on":[90,135,246],"reducing":[91],"overhead":[94],"by":[97,122,173,182,230],"avoiding":[98],"flush":[101],"before":[102],"replaying":[103],"executing":[107],"dependent":[108],"independent":[110],"concurrently.":[112],"The":[113],"goal":[114],"these":[116,198],"improvements":[117],"gain":[120],"performance":[121,210,222,244],"applying":[123],"L1":[126],"that":[130,217,238],"hit":[131],"last":[133],"level":[134],"chip":[136],"cache.":[137],"However,":[138],"many":[139],"applications":[140,145],"or":[141],"phases":[143],"incur":[146],"excessive":[147,189],"amount":[148],"replay":[150,185],"and/or":[151],"rollbacks":[152,192],"checkpoint.":[155,195],"This":[156],"frequently":[157],"cancels":[158],"benefits":[159],"reduces":[163],"performance.":[164],"In":[165],"this":[166],"article,":[167],"we":[168],"improve":[169],"architecture":[172,220,241],"using":[174,204],"novel":[176],"virtual":[177],"renaming":[179],"substrate":[180],"tuning":[183],"policies":[186],"mitigate":[188],"We":[196,235],"describe":[197],"new":[199],"design":[200],"optimizations":[201],"show,":[203],"Spec":[205],"2006":[206],"benchmarks":[207],"microarchitecture":[209],"power":[212],"models":[213],"our":[215,218,239],"design,":[216],"Tuned-CFP":[219],"improves":[221],"energy":[224,247],"consumption":[225],"over":[226],"previous":[227,258],"architectures":[229],"\u223c10%":[231],"\u223c8%,":[233],"respectively.":[234],"also":[236],"demonstrate":[237],"gives":[242],"better":[243],"return":[245],"per":[248],"instruction":[249],"compared":[250],"conventional":[253],"superscalar":[254],"as":[255,257],"well":[256],"architectures.":[260]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
