{"id":"https://openalex.org/W3022024970","doi":"https://doi.org/10.1109/tcad.2020.2992684","title":"Predictive Guardbanding: Program-Driven Timing Margin Reduction for GPUs","display_name":"Predictive Guardbanding: Program-Driven Timing Margin Reduction for GPUs","publication_year":2020,"publication_date":"2020-05-05","ids":{"openalex":"https://openalex.org/W3022024970","doi":"https://doi.org/10.1109/tcad.2020.2992684","mag":"3022024970"},"language":"en","primary_location":{"id":"doi:10.1109/tcad.2020.2992684","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcad.2020.2992684","pdf_url":null,"source":{"id":"https://openalex.org/S100835903","display_name":"IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems","issn_l":"0278-0070","issn":["0278-0070","1937-4151"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems","raw_type":"journal-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/A5003939279","display_name":"Jingwen Leng","orcid":"https://orcid.org/0000-0002-5660-5493"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jingwen Leng","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044824009","display_name":"Alper Buyuktosunoglu","orcid":"https://orcid.org/0000-0002-5341-8916"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alper Buyuktosunoglu","raw_affiliation_strings":["IBM T. J. Watson Research Center, IBM, Yorktown Heights, NY, USA"],"affiliations":[{"raw_affiliation_string":"IBM T. J. Watson Research Center, IBM, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017228661","display_name":"Ramon Bertran","orcid":"https://orcid.org/0000-0001-8297-1844"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ramon Bertran","raw_affiliation_strings":["IBM T. J. Watson Research Center, IBM, Yorktown Heights, NY, USA"],"affiliations":[{"raw_affiliation_string":"IBM T. J. Watson Research Center, IBM, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009866527","display_name":"Pradip Bose","orcid":"https://orcid.org/0000-0002-1380-5671"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pradip Bose","raw_affiliation_strings":["IBM T. J. Watson Research Center, IBM, Yorktown Heights, NY, USA"],"affiliations":[{"raw_affiliation_string":"IBM T. J. Watson Research Center, IBM, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020600861","display_name":"Yazhou Zu","orcid":"https://orcid.org/0000-0003-0047-6976"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yazhou Zu","raw_affiliation_strings":["Google, Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Google, Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000635267","display_name":"Vijay Janapa Reddi","orcid":"https://orcid.org/0000-0002-5259-7721"},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vijay Janapa Reddi","raw_affiliation_strings":["John A. Paulson School of Engineering and Applied Sciences, Harvard University, Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"John A. Paulson School of Engineering and Applied Sciences, Harvard University, Cambridge, MA, USA","institution_ids":["https://openalex.org/I136199984"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5003939279"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":2.0793,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.86541812,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":97},"biblio":{"volume":"40","issue":"1","first_page":"171","last_page":"184"},"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/T10363","display_name":"Low-power high-performance VLSI design","score":0.9990000128746033,"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":0.9966999888420105,"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":0.6017446517944336},{"id":"https://openalex.org/keywords/energy","display_name":"Energy (signal processing)","score":0.444953590631485},{"id":"https://openalex.org/keywords/chip","display_name":"Chip","score":0.4251033663749695},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16306215524673462},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.10304391384124756},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.10253450274467468}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6017446517944336},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.444953590631485},{"id":"https://openalex.org/C165005293","wikidata":"https://www.wikidata.org/wiki/Q1074500","display_name":"Chip","level":2,"score":0.4251033663749695},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16306215524673462},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.10304391384124756},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.10253450274467468}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcad.2020.2992684","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcad.2020.2992684","pdf_url":null,"source":{"id":"https://openalex.org/S100835903","display_name":"IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems","issn_l":"0278-0070","issn":["0278-0070","1937-4151"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.9200000166893005}],"awards":[{"id":"https://openalex.org/G1945030456","display_name":null,"funder_award_id":"HR0011-13-C-0022","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G5268805254","display_name":null,"funder_award_id":"CCF-1218474","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G753170689","display_name":null,"funder_award_id":"61702328","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306087","display_name":"Semiconductor Research Corporation","ror":"https://ror.org/047z4n946"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W1518236483","https://openalex.org/W1621319046","https://openalex.org/W1977476862","https://openalex.org/W1981384041","https://openalex.org/W1982700323","https://openalex.org/W1985918920","https://openalex.org/W1994172067","https://openalex.org/W1994805710","https://openalex.org/W1997162567","https://openalex.org/W2003128690","https://openalex.org/W2017099699","https://openalex.org/W2023304380","https://openalex.org/W2023571465","https://openalex.org/W2049303720","https://openalex.org/W2079706534","https://openalex.org/W2080592089","https://openalex.org/W2093043622","https://openalex.org/W2096486545","https://openalex.org/W2098163907","https://openalex.org/W2098764315","https://openalex.org/W2104677471","https://openalex.org/W2105560148","https://openalex.org/W2110422349","https://openalex.org/W2117608378","https://openalex.org/W2124256021","https://openalex.org/W2129904319","https://openalex.org/W2129960401","https://openalex.org/W2130720335","https://openalex.org/W2146731180","https://openalex.org/W2147042877","https://openalex.org/W2148952606","https://openalex.org/W2151943723","https://openalex.org/W2155893237","https://openalex.org/W2156331292","https://openalex.org/W2156665896","https://openalex.org/W2163605009","https://openalex.org/W2167244863","https://openalex.org/W2234633824","https://openalex.org/W2235375535","https://openalex.org/W2322662801","https://openalex.org/W2418749065","https://openalex.org/W2561349355","https://openalex.org/W2624897894","https://openalex.org/W2904147273","https://openalex.org/W2908348633","https://openalex.org/W2978697470","https://openalex.org/W3004415421","https://openalex.org/W3016875561","https://openalex.org/W3020414749","https://openalex.org/W4229759979","https://openalex.org/W4236432903","https://openalex.org/W4237720872","https://openalex.org/W6682349905","https://openalex.org/W6684191040"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2478288626","https://openalex.org/W2350741829","https://openalex.org/W2530322880","https://openalex.org/W1596801655"],"abstract_inverted_index":{"The":[0,185,196],"energy":[1,22,81],"efficiency":[2],"of":[3,12,24,85,207],"GPU":[4,27,53,88],"architectures":[5],"has":[6,136],"emerged":[7],"as":[8],"an":[9],"essential":[10],"aspect":[11],"computer":[13],"system":[14],"design.":[15],"In":[16],"this":[17],"article,":[18],"we":[19,167],"explore":[20],"the":[21,26,31,86,103,107,113,122,133,148,154,157,221,225],"benefits":[23],"reducing":[25],"chip's":[28],"voltage":[29,62,134,162,222],"to":[30,79,147,170,176],"safe":[32],"limit,":[33],"i.e.,":[34],"V":[35,97,124,142,179,198],"<sub":[36,98,125,143,180,199],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[37,99,126,144,181,200],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">min</sub>":[38,100,127,145,182,201],"point,":[39],"using":[40],"predictive":[41],"software":[42,217],"techniques.":[43],"We":[44,55,117,129],"perform":[45],"such":[46],"a":[47,94,137,208,231],"study":[48],"on":[49,64,83,112,141],"several":[50],"commercial":[51],"off-the-shelf":[52],"cards.":[54,89],"find":[56],"that":[57,132],"there":[58],"exists":[59],"about":[60,121],"20%":[61],"guardband":[63],"those":[65],"GPUs":[66],"spanning":[67],"two":[68],"architectural":[69],"generations,":[70],"which,":[71],"if":[72],"\u201celiminated\u201d":[73],"entirely,":[74],"can":[75],"result":[76],"in":[77,215],"up":[78,204],"25%":[80],"savings":[82],"one":[84],"studied":[87,104],"Our":[90],"measurement":[91],"results":[92],"unveil":[93],"program":[95],"dependent":[96],"behavior":[101],"across":[102],"applications,":[105],"and":[106,150,153,187,193,219],"exact":[108],"improvement":[109],"magnitude":[110],"depends":[111],"program's":[114],"available":[115],"guardband.":[116],"make":[118],"fundamental":[119],"observations":[120],"program-dependent":[123],"behavior.":[128],"experimentally":[130],"determine":[131],"noise":[135],"more":[138],"substantial":[139],"impact":[140],"compared":[146],"process":[149],"temperature":[151],"variation,":[152],"activities":[155],"during":[156],"kernel":[158],"execution":[159],"cause":[160],"large":[161],"droops.":[163],"From":[164],"these":[165],"findings,":[166],"show":[168],"how":[169],"use":[171],"kernels'":[172],"microarchitectural":[173],"performance":[174],"counters":[175],"predict":[177],"its":[178],"value":[183],"accurately.":[184],"average":[186],"maximum":[188],"prediction":[189,202],"errors":[190],"are":[191],"0.5%":[192],"3%,":[194],"respectively.":[195],"accurate":[197],"opens":[203],"new":[205],"possibilities":[206],"crosslayer":[209],"dynamic":[210],"guardbanding":[211],"scheme":[212],"for":[213],"GPUs,":[214],"which":[216],"predicts":[218],"manages":[220],"guardband,":[223],"while":[224],"functional":[226],"correctness":[227],"is":[228],"ensured":[229],"by":[230],"hardware":[232],"safety":[233],"net":[234],"mechanism.":[235]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}