{"id":"https://openalex.org/W3148457660","doi":"https://doi.org/10.1109/date.2012.6176483","title":"Run-time power-gating in caches of GPUs for leakage energy savings","display_name":"Run-time power-gating in caches of GPUs for leakage energy savings","publication_year":2012,"publication_date":"2012-03-01","ids":{"openalex":"https://openalex.org/W3148457660","doi":"https://doi.org/10.1109/date.2012.6176483","mag":"3148457660"},"language":"en","primary_location":{"id":"doi:10.1109/date.2012.6176483","is_oa":false,"landing_page_url":"https://doi.org/10.1109/date.2012.6176483","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 Design, Automation & Test in Europe Conference & Exhibition (DATE)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100371996","display_name":"Yue Wang","orcid":"https://orcid.org/0000-0002-1287-7710"},"institutions":[{"id":"https://openalex.org/I2613432","display_name":"University of South Florida","ror":"https://ror.org/032db5x82","country_code":"US","type":"education","lineage":["https://openalex.org/I2613432"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yue Wang","raw_affiliation_strings":["CSE Department, University of South Florida, Tampa, FL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CSE Department, University of South Florida, Tampa, FL, USA","institution_ids":["https://openalex.org/I2613432"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002347058","display_name":"Soumyaroop Roy","orcid":null},"institutions":[{"id":"https://openalex.org/I4210137977","display_name":"Advanced Micro Devices (United States)","ror":"https://ror.org/04kd6c783","country_code":"US","type":"company","lineage":["https://openalex.org/I4210137977"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"S. Roy","raw_affiliation_strings":["Advanced Micro Devices, Inc., Austin, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Micro Devices, Inc., Austin, TX, USA","institution_ids":["https://openalex.org/I4210137977"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027665366","display_name":"N. Ranganathan","orcid":null},"institutions":[{"id":"https://openalex.org/I2613432","display_name":"University of South Florida","ror":"https://ror.org/032db5x82","country_code":"US","type":"education","lineage":["https://openalex.org/I2613432"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"N. Ranganathan","raw_affiliation_strings":["CSE Department, University of South Florida, Tampa, FL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CSE Department, University of South Florida, Tampa, FL, USA","institution_ids":["https://openalex.org/I2613432"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3783,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.56284782,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"300","last_page":"303"},"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9970999956130981,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9965000152587891,"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/sleep-mode","display_name":"Sleep mode","score":0.8141021728515625},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.8086003065109253},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8013214468955994},{"id":"https://openalex.org/keywords/power-gating","display_name":"Power gating","score":0.7014161348342896},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5448825359344482},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5399447083473206},{"id":"https://openalex.org/keywords/cpu-cache","display_name":"CPU cache","score":0.4937609136104584},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.4809662401676178},{"id":"https://openalex.org/keywords/ibm","display_name":"IBM","score":0.47547951340675354},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.46870917081832886},{"id":"https://openalex.org/keywords/cache-algorithms","display_name":"Cache algorithms","score":0.4504127502441406},{"id":"https://openalex.org/keywords/microarchitecture","display_name":"Microarchitecture","score":0.4374702572822571},{"id":"https://openalex.org/keywords/instruction-set","display_name":"Instruction set","score":0.43573689460754395},{"id":"https://openalex.org/keywords/smart-cache","display_name":"Smart Cache","score":0.4253453016281128},{"id":"https://openalex.org/keywords/leakage","display_name":"Leakage (economics)","score":0.41524776816368103},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.3006092309951782},{"id":"https://openalex.org/keywords/transistor","display_name":"Transistor","score":0.19290196895599365},{"id":"https://openalex.org/keywords/power-consumption","display_name":"Power consumption","score":0.14579850435256958},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0840350091457367},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.07384541630744934}],"concepts":[{"id":"https://openalex.org/C57149124","wikidata":"https://www.wikidata.org/wiki/Q587346","display_name":"Sleep mode","level":4,"score":0.8141021728515625},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.8086003065109253},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8013214468955994},{"id":"https://openalex.org/C2780700455","wikidata":"https://www.wikidata.org/wiki/Q7236515","display_name":"Power gating","level":4,"score":0.7014161348342896},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5448825359344482},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5399447083473206},{"id":"https://openalex.org/C189783530","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"CPU cache","level":3,"score":0.4937609136104584},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.4809662401676178},{"id":"https://openalex.org/C70388272","wikidata":"https://www.wikidata.org/wiki/Q5968558","display_name":"IBM","level":2,"score":0.47547951340675354},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.46870917081832886},{"id":"https://openalex.org/C38556500","wikidata":"https://www.wikidata.org/wiki/Q13404475","display_name":"Cache algorithms","level":4,"score":0.4504127502441406},{"id":"https://openalex.org/C107598950","wikidata":"https://www.wikidata.org/wiki/Q259864","display_name":"Microarchitecture","level":2,"score":0.4374702572822571},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.43573689460754395},{"id":"https://openalex.org/C167713795","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"Smart Cache","level":5,"score":0.4253453016281128},{"id":"https://openalex.org/C2777042071","wikidata":"https://www.wikidata.org/wiki/Q6509304","display_name":"Leakage (economics)","level":2,"score":0.41524776816368103},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.3006092309951782},{"id":"https://openalex.org/C172385210","wikidata":"https://www.wikidata.org/wiki/Q5339","display_name":"Transistor","level":3,"score":0.19290196895599365},{"id":"https://openalex.org/C2984118289","wikidata":"https://www.wikidata.org/wiki/Q29954","display_name":"Power consumption","level":3,"score":0.14579850435256958},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0840350091457367},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.07384541630744934},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C139719470","wikidata":"https://www.wikidata.org/wiki/Q39680","display_name":"Macroeconomics","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C171250308","wikidata":"https://www.wikidata.org/wiki/Q11468","display_name":"Nanotechnology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/date.2012.6176483","is_oa":false,"landing_page_url":"https://doi.org/10.1109/date.2012.6176483","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 Design, Automation & Test in Europe Conference & Exhibition (DATE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8999999761581421,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W1979527452","https://openalex.org/W2114655921","https://openalex.org/W2150722965"],"related_works":["https://openalex.org/W2957999883","https://openalex.org/W2147511796","https://openalex.org/W2038398038","https://openalex.org/W2121761261","https://openalex.org/W2144466902","https://openalex.org/W1566654001","https://openalex.org/W2100115659","https://openalex.org/W2162888549","https://openalex.org/W2110014487","https://openalex.org/W3148457660"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"propose":[4],"a":[5,24,30,97,162],"novel":[6],"microarchitectural":[7],"technique":[8,84,114,184],"for":[9,80,150],"run-time":[10],"power-gating":[11],"caches":[12,71],"of":[13,92,120,146],"GPUs":[14],"to":[15,23,40,68,99],"save":[16],"leakage":[17],"energy.":[18],"The":[19,59,77,113,141],"L1":[20],"cache":[21,46,94,98,148],"(private":[22],"core)":[25],"can":[26,47],"be":[27,41,48],"put":[28,49],"in":[29,50,86,118],"low-leakage":[31],"sleep":[32,51,60,100],"mode":[33,52,61],"when":[34,53],"there":[35,54],"are":[36,74],"no":[37,56],"ready":[38],"threads":[39],"scheduled,":[42],"and":[43,101,122,143,155],"the":[44,66,70,81,87,90,128,138,147,152,156,176,182],"L2":[45],"is":[55,62,107,109,159,185],"memory":[57],"request.":[58],"state-retentive,":[63],"which":[64],"precludes":[65],"necessity":[67],"flush":[69],"after":[72],"they":[73],"woken":[75],"up.":[76],"primary":[78],"reason":[79],"effectiveness":[82],"our":[83],"lies":[85],"fact":[88],"that":[89,133],"latency":[91,144,154],"detecting":[93],"inactivity,":[95],"putting":[96],"waking":[102],"it":[103,106],"up":[104,136],"before":[105],"accessed,":[108],"completely":[110],"hidden":[111],"microarchitecturally.":[112],"incurs":[115],"insignificant":[116],"overheads":[117],"terms":[119],"power":[121,142],"area.":[123],"Experiments":[124],"were":[125],"performed":[126,160],"using":[127,137,161],"GPGPU-Sim":[129],"simulator":[130],"on":[131,169,171],"benchmarks":[132],"was":[134],"set":[135],"CUDA":[139],"framework.":[140],"modeling":[145],"arrays":[149],"measuring":[151],"wake-up":[153],"break-even":[157],"periods":[158],"32-nm":[163],"SOI":[164],"IBM":[165],"technology":[166],"model.":[167],"Based":[168],"experiments":[170],"16":[172],"different":[173],"GPU":[174],"workloads,":[175],"average":[177],"energy":[178],"savings":[179],"achieved":[180],"by":[181],"proposed":[183],"54%.":[186]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2014,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}