{"id":"https://openalex.org/W4414538873","doi":"https://doi.org/10.1109/icc52391.2025.11161883","title":"DVFS-Aware DNN Inference on GPUs: Latency Modeling and Performance Analysis","display_name":"DVFS-Aware DNN Inference on GPUs: Latency Modeling and Performance Analysis","publication_year":2025,"publication_date":"2025-06-08","ids":{"openalex":"https://openalex.org/W4414538873","doi":"https://doi.org/10.1109/icc52391.2025.11161883"},"language":"en","primary_location":{"id":"doi:10.1109/icc52391.2025.11161883","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icc52391.2025.11161883","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICC 2025 - IEEE International Conference on Communications","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/A5064882937","display_name":"Yunseok Han","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yunchu Han","raw_affiliation_strings":["Tsinghua University,Beijing National Research Center for Information Science and Technology,Department of Electronic Engineering,Beijing,China,100084"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Beijing National Research Center for Information Science and Technology,Department of Electronic Engineering,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014585995","display_name":"Zhaojun Nan","orcid":"https://orcid.org/0000-0003-1487-2179"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhaojun Nan","raw_affiliation_strings":["Tsinghua University,Beijing National Research Center for Information Science and Technology,Department of Electronic Engineering,Beijing,China,100084"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Beijing National Research Center for Information Science and Technology,Department of Electronic Engineering,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021120517","display_name":"Sheng Zhou","orcid":"https://orcid.org/0000-0003-0651-0071"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sheng Zhou","raw_affiliation_strings":["Tsinghua University,Beijing National Research Center for Information Science and Technology,Department of Electronic Engineering,Beijing,China,100084"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Beijing National Research Center for Information Science and Technology,Department of Electronic Engineering,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034505506","display_name":"Zhisheng Niu","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhisheng Niu","raw_affiliation_strings":["Tsinghua University,Beijing National Research Center for Information Science and Technology,Department of Electronic Engineering,Beijing,China,100084"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Beijing National Research Center for Information Science and Technology,Department of Electronic Engineering,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5064882937"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":4.8723,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.95573882,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1274","last_page":"1279"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9915000200271606,"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":0.9915000200271606,"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/T12702","display_name":"Brain Tumor Detection and Classification","score":0.9909999966621399,"subfield":{"id":"https://openalex.org/subfields/2808","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T12676","display_name":"Machine Learning and ELM","score":0.9133999943733215,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/inference","display_name":"Inference","score":0.9121000170707703},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.6603999733924866},{"id":"https://openalex.org/keywords/energy-consumption","display_name":"Energy consumption","score":0.6312999725341797},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4521999955177307},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.40610000491142273},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.3720000088214874},{"id":"https://openalex.org/keywords/voltage-reduction","display_name":"Voltage reduction","score":0.36160001158714294},{"id":"https://openalex.org/keywords/efficient-energy-use","display_name":"Efficient energy use","score":0.3418000042438507}],"concepts":[{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.9121000170707703},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7735000252723694},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.6603999733924866},{"id":"https://openalex.org/C2780165032","wikidata":"https://www.wikidata.org/wiki/Q16869822","display_name":"Energy consumption","level":2,"score":0.6312999725341797},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4521999955177307},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44429999589920044},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.40610000491142273},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.3720000088214874},{"id":"https://openalex.org/C2780745134","wikidata":"https://www.wikidata.org/wiki/Q7940751","display_name":"Voltage reduction","level":3,"score":0.36160001158714294},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35839998722076416},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.3418000042438507},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.3280999958515167},{"id":"https://openalex.org/C134261354","wikidata":"https://www.wikidata.org/wiki/Q938438","display_name":"Statistical inference","level":2,"score":0.32760000228881836},{"id":"https://openalex.org/C186108316","wikidata":"https://www.wikidata.org/wiki/Q352530","display_name":"Adaptive neuro fuzzy inference system","level":4,"score":0.3093000054359436},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.2971000075340271},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2881999909877777},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.28630000352859497},{"id":"https://openalex.org/C95167961","wikidata":"https://www.wikidata.org/wiki/Q4483495","display_name":"Fiducial inference","level":5,"score":0.25870001316070557},{"id":"https://openalex.org/C33553690","wikidata":"https://www.wikidata.org/wiki/Q17014702","display_name":"Free energy principle","level":2,"score":0.2563000023365021},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.2524999976158142}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icc52391.2025.11161883","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icc52391.2025.11161883","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICC 2025 - IEEE International Conference on Communications","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3398910123","display_name":null,"funder_award_id":"2023M742011","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"},{"id":"https://openalex.org/G7423065200","display_name":null,"funder_award_id":"62341108","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W2026929743","https://openalex.org/W2194775991","https://openalex.org/W2565516711","https://openalex.org/W2624989916","https://openalex.org/W2770165898","https://openalex.org/W2789836338","https://openalex.org/W2950865323","https://openalex.org/W3080950018","https://openalex.org/W3110777925","https://openalex.org/W3174661481","https://openalex.org/W4214866088","https://openalex.org/W4282934545","https://openalex.org/W4285263159","https://openalex.org/W4312864291","https://openalex.org/W4321194942","https://openalex.org/W4407212671"],"related_works":[],"abstract_inverted_index":{"The":[0],"rapid":[1],"development":[2],"of":[3,14,40,48,54,122,172],"deep":[4],"neural":[5],"networks":[6],"(DNNs)":[7],"is":[8,27,141],"inherently":[9],"accompanied":[10],"by":[11,43,126],"the":[12,35,45,61,67,106,120,134,138,151,196,201,206],"problem":[13],"high":[15],"computational":[16],"costs.":[17],"To":[18],"tackle":[19],"this":[20,87],"challenge,":[21],"dynamic":[22],"voltage":[23],"frequency":[24,47],"scaling":[25],"(DVFS)":[26],"emerging":[28],"as":[29],"a":[30,91,170],"promising":[31],"technology":[32],"for":[33,115],"balancing":[34],"latency":[36,82,93],"and":[37,64,83,118,132,177,182,199],"energy":[38,84,183,202],"consumption":[39,184,203],"DNN":[41,55,71,98,107],"inference":[42,56,72,99,108,136,163,180,189],"adjusting":[44],"computing":[46],"processors.":[49],"However,":[50],"most":[51],"existing":[52],"models":[53],"time":[57,100,109,181],"are":[58],"based":[59,110],"on":[60,73,101,111],"CPU-DVFS":[62,152],"technique,":[63],"directly":[65],"applying":[66],"CPUDVFS":[68,207],"model":[69,94,140,149,153,168,193],"to":[70,77,95,205],"GPUs":[74],"will":[75],"lead":[76],"significant":[78],"errors":[79],"in":[80,154,179],"optimizing":[81],"consumption.":[85],"In":[86,186],"paper,":[88],"we":[89,145],"propose":[90],"DVFS-aware":[92],"precisely":[96],"characterize":[97],"GPUs.":[102],"We":[103],"first":[104],"formulate":[105],"extensive":[112],"experiment":[113],"results":[114,159],"different":[116],"devices":[117],"analyze":[119],"impact":[121],"fitting":[123],"parameters.":[124],"Then":[125],"dividing":[127],"DNNs":[128],"into":[129],"multiple":[130],"blocks":[131],"obtaining":[133],"actual":[135],"time,":[137],"proposed":[139,148,167,192],"further":[142],"verified.":[143],"Finally,":[144],"compare":[146],"our":[147,166,191],"with":[150,165,190],"two":[155],"specific":[156],"cases.":[157],"Evaluation":[158],"demonstrate":[160],"that":[161],"local":[162],"optimization":[164],"achieves":[169],"reduction":[171],"no":[173],"less":[174],"than":[175],"66%":[176],"69%":[178],"respectively.":[185],"addition,":[187],"cooperative":[188],"can":[194],"improve":[195],"partition":[197],"policy":[198],"reduce":[200],"compared":[204],"model.":[208]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}