{"id":"https://openalex.org/W2093043622","doi":"https://doi.org/10.1145/2485922.2485964","title":"GPUWattch","display_name":"GPUWattch","publication_year":2013,"publication_date":"2013-06-23","ids":{"openalex":"https://openalex.org/W2093043622","doi":"https://doi.org/10.1145/2485922.2485964","mag":"2093043622"},"language":"en","primary_location":{"id":"doi:10.1145/2485922.2485964","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2485922.2485964","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 40th Annual International Symposium on Computer Architecture","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/A5003939279","display_name":"Jingwen Leng","orcid":"https://orcid.org/0000-0002-5660-5493"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jingwen Leng","raw_affiliation_strings":["The University of Texas at Austin","The University of Texas, at Austin"],"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]},{"raw_affiliation_string":"The University of Texas, at Austin","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034060699","display_name":"Tayler Hetherington","orcid":null},"institutions":[{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Tayler Hetherington","raw_affiliation_strings":["University of British Columbia"],"affiliations":[{"raw_affiliation_string":"University of British Columbia","institution_ids":["https://openalex.org/I141945490"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112356504","display_name":"Ahmed ElTantawy","orcid":null},"institutions":[{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Ahmed ElTantawy","raw_affiliation_strings":["University of British Columbia"],"affiliations":[{"raw_affiliation_string":"University of British Columbia","institution_ids":["https://openalex.org/I141945490"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061356872","display_name":"Syed Gilani","orcid":"https://orcid.org/0000-0003-3129-3363"},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Syed Gilani","raw_affiliation_strings":["University of Wisconsin-Madison","University of Wisconsin, Madison"],"affiliations":[{"raw_affiliation_string":"University of Wisconsin-Madison","institution_ids":["https://openalex.org/I135310074"]},{"raw_affiliation_string":"University of Wisconsin, Madison","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037648751","display_name":"Nam Sung Kim","orcid":"https://orcid.org/0000-0002-0442-5634"},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nam Sung Kim","raw_affiliation_strings":["University of Wisconsin-Madison","University of Wisconsin, Madison"],"affiliations":[{"raw_affiliation_string":"University of Wisconsin-Madison","institution_ids":["https://openalex.org/I135310074"]},{"raw_affiliation_string":"University of Wisconsin, Madison","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026788167","display_name":"Tor M. Aamodt","orcid":"https://orcid.org/0000-0003-1161-692X"},"institutions":[{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Tor M. Aamodt","raw_affiliation_strings":["University of British Columbia"],"affiliations":[{"raw_affiliation_string":"University of British Columbia","institution_ids":["https://openalex.org/I141945490"]}]},{"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/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vijay Janapa Reddi","raw_affiliation_strings":["The University of Texas at Austin","The University of Texas, at Austin"],"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]},{"raw_affiliation_string":"The University of Texas, at Austin","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5003939279"],"corresponding_institution_ids":["https://openalex.org/I86519309"],"apc_list":null,"apc_paid":null,"fwci":68.5895,"has_fulltext":false,"cited_by_count":496,"citation_normalized_percentile":{"value":1.0,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"487","last_page":"498"},"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9975000023841858,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9968000054359436,"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":0.8272258043289185},{"id":"https://openalex.org/keywords/frequency-scaling","display_name":"Frequency scaling","score":0.7396373152732849},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.6215868592262268},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5713011622428894},{"id":"https://openalex.org/keywords/energy-consumption","display_name":"Energy consumption","score":0.551903247833252},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5465434193611145},{"id":"https://openalex.org/keywords/clock-gating","display_name":"Clock gating","score":0.5423203110694885},{"id":"https://openalex.org/keywords/efficient-energy-use","display_name":"Efficient energy use","score":0.5178382992744446},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.5176092386245728},{"id":"https://openalex.org/keywords/dynamic-demand","display_name":"Dynamic demand","score":0.4952634871006012},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.47241702675819397},{"id":"https://openalex.org/keywords/performance-metric","display_name":"Performance metric","score":0.4402191936969757},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.4318876564502716},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.4192078709602356},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.2360553741455078},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.16233539581298828},{"id":"https://openalex.org/keywords/clock-skew","display_name":"Clock skew","score":0.11641019582748413},{"id":"https://openalex.org/keywords/clock-signal","display_name":"Clock signal","score":0.08731156587600708}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8272258043289185},{"id":"https://openalex.org/C157742956","wikidata":"https://www.wikidata.org/wiki/Q3237776","display_name":"Frequency scaling","level":3,"score":0.7396373152732849},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.6215868592262268},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5713011622428894},{"id":"https://openalex.org/C2780165032","wikidata":"https://www.wikidata.org/wiki/Q16869822","display_name":"Energy consumption","level":2,"score":0.551903247833252},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5465434193611145},{"id":"https://openalex.org/C22716491","wikidata":"https://www.wikidata.org/wiki/Q590170","display_name":"Clock gating","level":5,"score":0.5423203110694885},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.5178382992744446},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.5176092386245728},{"id":"https://openalex.org/C45872418","wikidata":"https://www.wikidata.org/wiki/Q5318966","display_name":"Dynamic demand","level":3,"score":0.4952634871006012},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.47241702675819397},{"id":"https://openalex.org/C2780898871","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Performance metric","level":2,"score":0.4402191936969757},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.4318876564502716},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.4192078709602356},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.2360553741455078},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.16233539581298828},{"id":"https://openalex.org/C60501442","wikidata":"https://www.wikidata.org/wiki/Q4382014","display_name":"Clock skew","level":4,"score":0.11641019582748413},{"id":"https://openalex.org/C137059387","wikidata":"https://www.wikidata.org/wiki/Q426882","display_name":"Clock signal","level":3,"score":0.08731156587600708},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"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},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C134652429","wikidata":"https://www.wikidata.org/wiki/Q1052698","display_name":"Jitter","level":2,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2485922.2485964","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2485922.2485964","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 40th Annual International Symposium on Computer Architecture","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.9100000262260437}],"awards":[{"id":"https://openalex.org/G6687181254","display_name":null,"funder_award_id":"CCF-1218474, CCF-0953603, CNS-1217102","funder_id":"https://openalex.org/F4320337388","funder_display_name":"Division of Computer and Network Systems"},{"id":"https://openalex.org/G8048678911","display_name":null,"funder_award_id":"CCF-1218474, CCF-0953603, CNS-1217102","funder_id":"https://openalex.org/F4320337387","funder_display_name":"Division of Computing and Communication Foundations"}],"funders":[{"id":"https://openalex.org/F4320307102","display_name":"Intel Corporation","ror":"https://ror.org/01ek73717"},{"id":"https://openalex.org/F4320307757","display_name":"Advanced Micro Devices","ror":"https://ror.org/04kd6c783"},{"id":"https://openalex.org/F4320337387","display_name":"Division of Computing and Communication Foundations","ror":"https://ror.org/01mng8331"},{"id":"https://openalex.org/F4320337388","display_name":"Division of Computer and Network Systems","ror":"https://ror.org/02rdzmk74"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1482635212","https://openalex.org/W1903794615","https://openalex.org/W1978969737","https://openalex.org/W1979527452","https://openalex.org/W1997962045","https://openalex.org/W2019104751","https://openalex.org/W2033597569","https://openalex.org/W2049875313","https://openalex.org/W2066804546","https://openalex.org/W2080592089","https://openalex.org/W2081140905","https://openalex.org/W2090584832","https://openalex.org/W2100799944","https://openalex.org/W2101903894","https://openalex.org/W2102727118","https://openalex.org/W2103742924","https://openalex.org/W2115412309","https://openalex.org/W2116175063","https://openalex.org/W2118214977","https://openalex.org/W2122297544","https://openalex.org/W2134953833","https://openalex.org/W2155503253","https://openalex.org/W2155568054","https://openalex.org/W2161537396","https://openalex.org/W2164586147","https://openalex.org/W2169880332","https://openalex.org/W2170382128","https://openalex.org/W2173313568","https://openalex.org/W2271718427","https://openalex.org/W3145579537","https://openalex.org/W3146061826"],"related_works":["https://openalex.org/W2539473121","https://openalex.org/W2941526850","https://openalex.org/W2960456644","https://openalex.org/W2909194634","https://openalex.org/W2485892467","https://openalex.org/W2312282667","https://openalex.org/W2027268352","https://openalex.org/W1652198943","https://openalex.org/W4252084893","https://openalex.org/W1972953980"],"abstract_inverted_index":{"General-purpose":[0],"GPUs":[1,130],"(GPGPUs)":[2],"are":[3],"becoming":[4],"prevalent":[5],"in":[6],"mainstream":[7],"computing,":[8],"and":[9,60,75,102,117,124,133,157,166,170],"performance":[10],"per":[11],"watt":[12],"has":[13],"emerged":[14],"as":[15,82],"a":[16,48,72,88],"more":[17],"crucial":[18],"evaluation":[19],"metric":[20],"than":[21],"peak":[22],"performance.":[23],"As":[24],"such,":[25],"GPU":[26,176],"architects":[27],"require":[28],"robust":[29],"tools":[30],"that":[31,53,94,202,210],"will":[32],"enable":[33],"them":[34],"to":[35,40,97,197],"quickly":[36],"explore":[37],"new":[38,49],"ways":[39],"optimize":[41],"GPGPUs":[42],"for":[43,126,199],"energy":[44,160,177,193],"efficiency.":[45],"We":[46,86,147,207],"propose":[47],"GPGPU":[50],"power":[51,105,142,150,219],"model":[52,106,137,151],"is":[54,107,121],"configurable,":[55],"capable":[56],"of":[57,91,112],"cycle-level":[58,154],"calculations,":[59],"carefully":[61],"validated":[62,109],"against":[63,110],"real":[64],"hardware":[65],"measurements.":[66],"To":[67],"achieve":[68],"configurability,":[69],"we":[70,95],"use":[71,96],"bottom-up":[73],"methodology":[74],"abstract":[76],"parameters":[77],"from":[78,195],"the":[79,83,118,127,141,149,153,159,192],"microarchitectural":[80],"components":[81],"model's":[84],"inputs.":[85],"developed":[87],"rigorous":[89],"suite":[90],"80":[92],"microbenchmarks":[93],"bound":[98],"any":[99],"modeling":[100],"uncertainties":[101],"inaccuracies.":[103],"The":[104,136],"comprehensively":[108],"measurements":[111],"two":[113,128],"commercially":[114],"available":[115],"GPUs,":[116],"measured":[119],"error":[120],"within":[122],"9.9%":[123],"13.4%":[125],"target":[129],"(GTX":[131],"480":[132],"Quadro":[134],"FX5600).":[135],"also":[138,208],"accurately":[139],"tracks":[140],"consumption":[143,178],"trend":[144],"over":[145],"time.":[146],"integrated":[148],"with":[152],"simulator":[155],"GPGPU-Sim":[156],"demonstrate":[158],"savings":[161,194],"by":[162,179,181,220],"utilizing":[163],"dynamic":[164,218],"voltage":[165],"frequency":[167],"scaling":[168],"(DVFS)":[169],"clock":[171,211],"gating.":[172],"Traditional":[173],"DVFS":[174,190],"reduces":[175,217],"14.4%":[180],"leveraging":[182],"within-kernel":[183],"runtime":[184],"variations.":[185],"More":[186],"finer-grained":[187],"SM":[188],"cluster-level":[189],"improves":[191],"6.6%":[196],"13.6%":[198],"those":[200],"benchmarks":[201],"show":[203,209],"clustered":[204],"execution":[205],"behavior.":[206],"gating":[212],"inactive":[213],"lanes":[214],"during":[215],"divergence":[216],"11.2%.":[221]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":13},{"year":2022,"cited_by_count":14},{"year":2021,"cited_by_count":18},{"year":2020,"cited_by_count":47},{"year":2019,"cited_by_count":54},{"year":2018,"cited_by_count":63},{"year":2017,"cited_by_count":59},{"year":2016,"cited_by_count":76},{"year":2015,"cited_by_count":65},{"year":2014,"cited_by_count":58},{"year":2013,"cited_by_count":13}],"updated_date":"2026-03-29T08:15:47.926485","created_date":"2016-06-24T00:00:00"}