{"id":"https://openalex.org/W2902700387","doi":"https://doi.org/10.1109/hpec.2018.8547526","title":"Energy-Efficient DNN Computing on GPUs Through Register File Management","display_name":"Energy-Efficient DNN Computing on GPUs Through Register File Management","publication_year":2018,"publication_date":"2018-09-01","ids":{"openalex":"https://openalex.org/W2902700387","doi":"https://doi.org/10.1109/hpec.2018.8547526","mag":"2902700387"},"language":"en","primary_location":{"id":"doi:10.1109/hpec.2018.8547526","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec.2018.8547526","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE High Performance extreme Computing Conference (HPEC)","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/A5100327844","display_name":"Xin Wang","orcid":"https://orcid.org/0000-0001-8639-3818"},"institutions":[{"id":"https://openalex.org/I184840846","display_name":"Virginia Commonwealth University","ror":"https://ror.org/02nkdxk79","country_code":"US","type":"education","lineage":["https://openalex.org/I184840846"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xin Wang","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Virginia Commonwealth University, Richmond, VA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Virginia Commonwealth University, Richmond, VA","institution_ids":["https://openalex.org/I184840846"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103195719","display_name":"Wei Zhang","orcid":"https://orcid.org/0000-0002-4628-8893"},"institutions":[{"id":"https://openalex.org/I184840846","display_name":"Virginia Commonwealth University","ror":"https://ror.org/02nkdxk79","country_code":"US","type":"education","lineage":["https://openalex.org/I184840846"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wei Zhang","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Virginia Commonwealth University, Richmond, VA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Virginia Commonwealth University, Richmond, VA","institution_ids":["https://openalex.org/I184840846"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I184840846"],"apc_list":null,"apc_paid":null,"fwci":0.0761,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.40528862,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"26","issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9994999766349792,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9991999864578247,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/register-file","display_name":"Register file","score":0.8379248380661011},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8278950452804565},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7425178289413452},{"id":"https://openalex.org/keywords/energy-consumption","display_name":"Energy consumption","score":0.6710366010665894},{"id":"https://openalex.org/keywords/efficient-energy-use","display_name":"Efficient energy use","score":0.5921132564544678},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.527903139591217},{"id":"https://openalex.org/keywords/operand","display_name":"Operand","score":0.5067716240882874},{"id":"https://openalex.org/keywords/frequency-scaling","display_name":"Frequency scaling","score":0.484164297580719},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.44636744260787964},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.4164007604122162},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.3368278741836548},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.3238886594772339},{"id":"https://openalex.org/keywords/instruction-set","display_name":"Instruction set","score":0.18257975578308105},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.1213054358959198}],"concepts":[{"id":"https://openalex.org/C117280010","wikidata":"https://www.wikidata.org/wiki/Q180944","display_name":"Register file","level":3,"score":0.8379248380661011},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8278950452804565},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7425178289413452},{"id":"https://openalex.org/C2780165032","wikidata":"https://www.wikidata.org/wiki/Q16869822","display_name":"Energy consumption","level":2,"score":0.6710366010665894},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.5921132564544678},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.527903139591217},{"id":"https://openalex.org/C55526617","wikidata":"https://www.wikidata.org/wiki/Q719375","display_name":"Operand","level":2,"score":0.5067716240882874},{"id":"https://openalex.org/C157742956","wikidata":"https://www.wikidata.org/wiki/Q3237776","display_name":"Frequency scaling","level":3,"score":0.484164297580719},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.44636744260787964},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.4164007604122162},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3368278741836548},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.3238886594772339},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.18257975578308105},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1213054358959198},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"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/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hpec.2018.8547526","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec.2018.8547526","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE High Performance extreme Computing Conference (HPEC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.9100000262260437,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W992687842","https://openalex.org/W1516536978","https://openalex.org/W1979527452","https://openalex.org/W1991518265","https://openalex.org/W2019427687","https://openalex.org/W2026186397","https://openalex.org/W2059301531","https://openalex.org/W2093043622","https://openalex.org/W2104761433","https://openalex.org/W2115157620","https://openalex.org/W2119144962","https://openalex.org/W2119306965","https://openalex.org/W2125647168","https://openalex.org/W2131054871","https://openalex.org/W2138777150","https://openalex.org/W2163605009","https://openalex.org/W2164474450","https://openalex.org/W2495425901","https://openalex.org/W2499540656","https://openalex.org/W2516141709","https://openalex.org/W2534060050","https://openalex.org/W2755395451","https://openalex.org/W2805642345","https://openalex.org/W2963981420","https://openalex.org/W2964217848","https://openalex.org/W2964299589","https://openalex.org/W4234833047","https://openalex.org/W4241441655","https://openalex.org/W4248310916","https://openalex.org/W4250945092","https://openalex.org/W6655548987","https://openalex.org/W6677922359","https://openalex.org/W6684191040","https://openalex.org/W6724998850"],"related_works":["https://openalex.org/W2105325426","https://openalex.org/W2245451942","https://openalex.org/W2088203538","https://openalex.org/W2116521658","https://openalex.org/W1580009706","https://openalex.org/W2100504584","https://openalex.org/W2763549657","https://openalex.org/W2123413169","https://openalex.org/W4246431097","https://openalex.org/W4248763955"],"abstract_inverted_index":{"Current":[0],"Deep":[1],"Neural":[2],"Networks(DNNs)":[3],"that":[4,127,216],"involve":[5],"a":[6,29,130,142,160,208],"mass":[7],"of":[8,39,52,77,79,133,181,184,195,219],"matrix":[9],"multiplications":[10],"and":[11,19,54,100,187,223,237],"other":[12],"similar":[13],"operations":[14],"can":[15,35,106],"be":[16],"well":[17],"paralleled":[18],"thus":[20,101],"accelerated":[21],"by":[22,178],"GPUs.":[23],"However,":[24],"energy":[25,61,98,111,167,176,202,231],"consumption":[26,99,112,232],"is":[27,68,87,207],"still":[28],"big":[30],"concern":[31],"for":[32,71,119],"DNN,":[33],"which":[34,86,206],"limit":[36],"the":[37,49,55,83,116,125,149,156,165,182,193,217,220,227],"scalability":[38],"performance":[40],"increase.":[41],"In":[42],"this":[43],"paper,":[44],"we":[45,138,154,170],"propose":[46,139],"to":[47,59,74,95,109,140,147,163,172,235],"utilize":[48],"specific":[50],"micro-architectures":[51],"GPUs":[53,73,96,108],"DNN":[56,210],"application":[57],"characteristics":[58],"improve":[60,174],"efficiency.":[62],"A":[63],"huge":[64],"register":[65,144,188,221],"file":[66],"(RF)":[67],"often":[69],"necessary":[70],"modern":[72],"hold":[75],"contexts":[76],"thousands":[78],"concurrent":[80],"threads.":[81],"Consequently,":[82],"GPU":[84,143,197,230],"RF":[85,103,150,158,175,186,198],"constructed":[88],"with":[89,159],"high":[90],"leakage":[91,166],"transistors":[92],"contributes":[93],"significantly":[94],"total":[97,229],"smart":[102],"management":[104,199],"strategies":[105],"help":[107],"reduce":[110],"when":[113],"scaling":[114],"up":[115,234],"hardware":[117],"resources":[118],"enhanced":[120],"performance.":[121],"First,":[122],"based":[123],"on":[124,201,239],"observation":[126],"there":[128],"are":[129],"large":[131],"fraction":[132],"narrow-width":[134],"operands":[135],"in":[136],"DNNs,":[137],"use":[141,148],"packing":[145,189,222],"scheme":[146],"more":[151],"efficiently.":[152],"Second,":[153],"introduce":[155],"drowsy":[157,185,224],"simple":[161],"policy":[162],"decrease":[164],"consumption.":[168],"Finally,":[169],"attempt":[171],"further":[173],"efficiency":[177],"taking":[179],"advantage":[180],"cooperation":[183],"techniques.":[190],"We":[191],"evaluate":[192],"effectiveness":[194],"our":[196],"schemes":[200],"reduction":[203],"using":[204],"AlexNet":[205],"state-of-the-art":[209],"model.":[211],"The":[212],"experimental":[213],"results":[214],"show":[215],"combination":[218],"techniques":[225],"achieves":[226],"most":[228],"reduction,":[233],"11%":[236],"10.3%":[238],"average.":[240]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}