{"id":"https://openalex.org/W3084790829","doi":"https://doi.org/10.1109/lca.2020.3023723","title":"GPU-NEST: Characterizing Energy Efficiency of Multi-GPU Inference Servers","display_name":"GPU-NEST: Characterizing Energy Efficiency of Multi-GPU Inference Servers","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W3084790829","doi":"https://doi.org/10.1109/lca.2020.3023723","mag":"3084790829"},"language":"en","primary_location":{"id":"doi:10.1109/lca.2020.3023723","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lca.2020.3023723","pdf_url":null,"source":{"id":"https://openalex.org/S17643076","display_name":"IEEE Computer Architecture Letters","issn_l":"1556-6056","issn":["1556-6056","1556-6064","2473-2575"],"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 Computer Architecture Letters","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/A5004077070","display_name":"Ali Jahanshahi","orcid":"https://orcid.org/0000-0002-4301-7588"},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ali Jahanshahi","raw_affiliation_strings":["University of California Riverside, Riverside, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-4301-7588","affiliations":[{"raw_affiliation_string":"University of California Riverside, Riverside, CA, USA","institution_ids":["https://openalex.org/I103635307"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010378286","display_name":"Hadi Zamani Sabzi","orcid":null},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hadi Zamani Sabzi","raw_affiliation_strings":["University of California Riverside, Riverside, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California Riverside, Riverside, CA, USA","institution_ids":["https://openalex.org/I103635307"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057951443","display_name":"Chester Lau","orcid":"https://orcid.org/0000-0002-0958-5557"},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chester Lau","raw_affiliation_strings":["University of California Riverside, Riverside, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California Riverside, Riverside, CA, USA","institution_ids":["https://openalex.org/I103635307"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000712719","display_name":"Daniel Wong","orcid":"https://orcid.org/0000-0002-5376-7868"},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Wong","raw_affiliation_strings":["University of California Riverside, Riverside, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California Riverside, Riverside, CA, USA","institution_ids":["https://openalex.org/I103635307"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":8.3545,"has_fulltext":false,"cited_by_count":44,"citation_normalized_percentile":{"value":0.97645218,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"19","issue":"2","first_page":"139","last_page":"142"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9987000226974487,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9984999895095825,"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/computer-science","display_name":"Computer science","score":0.8611613512039185},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.7920762300491333},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.6915223598480225},{"id":"https://openalex.org/keywords/efficient-energy-use","display_name":"Efficient energy use","score":0.6040600538253784},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.5503201484680176},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.5162063241004944},{"id":"https://openalex.org/keywords/energy-consumption","display_name":"Energy consumption","score":0.5060068964958191},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.47958245873451233},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.46840402483940125},{"id":"https://openalex.org/keywords/server","display_name":"Server","score":0.4358944892883301},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.39737558364868164},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.22834649682044983},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1858321726322174},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.10975399613380432},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.0869189202785492},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.0771636962890625}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8611613512039185},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7920762300491333},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.6915223598480225},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.6040600538253784},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5503201484680176},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.5162063241004944},{"id":"https://openalex.org/C2780165032","wikidata":"https://www.wikidata.org/wiki/Q16869822","display_name":"Energy consumption","level":2,"score":0.5060068964958191},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.47958245873451233},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.46840402483940125},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.4358944892883301},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.39737558364868164},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.22834649682044983},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1858321726322174},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.10975399613380432},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.0869189202785492},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.0771636962890625},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","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/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lca.2020.3023723","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lca.2020.3023723","pdf_url":null,"source":{"id":"https://openalex.org/S17643076","display_name":"IEEE Computer Architecture Letters","issn_l":"1556-6056","issn":["1556-6056","1556-6064","2473-2575"],"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 Computer Architecture Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.8999999761581421}],"awards":[],"funders":[{"id":"https://openalex.org/F4320332550","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2105477603","https://openalex.org/W2479666647","https://openalex.org/W2509498309","https://openalex.org/W2614226686","https://openalex.org/W2740507444","https://openalex.org/W2770891419","https://openalex.org/W2790957308","https://openalex.org/W2798789966","https://openalex.org/W2896248399","https://openalex.org/W2906773779","https://openalex.org/W2915358162","https://openalex.org/W2933147490","https://openalex.org/W2933483662","https://openalex.org/W2945148926","https://openalex.org/W2949981335","https://openalex.org/W2953736860","https://openalex.org/W2971357983","https://openalex.org/W3026199322","https://openalex.org/W4235551121","https://openalex.org/W4289083201","https://openalex.org/W6757364461"],"related_works":["https://openalex.org/W1657880117","https://openalex.org/W2595172197","https://openalex.org/W2127970246","https://openalex.org/W2084856301","https://openalex.org/W1001352512","https://openalex.org/W4382618745","https://openalex.org/W2885125400","https://openalex.org/W4214747436","https://openalex.org/W2953002963","https://openalex.org/W1915823365"],"abstract_inverted_index":{"Cloud":[0],"inference":[1,29,61,76,92,99,106],"systems":[2,30],"have":[3,50],"recently":[4],"emerged":[5],"as":[6,122,124],"a":[7,35],"solution":[8],"to":[9,42,49],"the":[10,17,54,83,115],"ever-increasing":[11],"integration":[12],"of":[13,25,59,118],"AI-powered":[14],"applications":[15],"into":[16,53],"smart":[18],"devices":[19],"around":[20],"us.":[21],"The":[22],"wide":[23],"adoption":[24],"GPUs":[26],"in":[27,38,108,113],"cloud":[28],"has":[31,110],"made":[32],"power":[33,55],"consumption":[34],"first-order":[36],"constraint":[37],"multi-GPU":[39,60,75,90,98,119],"systems.":[40,77],"Thus,":[41],"achieve":[43],"this":[44,64],"goal,":[45],"it":[46],"is":[47],"critical":[48],"better":[51],"insight":[52],"and":[56,87,94],"performance":[57],"behaviors":[58],"system.":[62],"To":[63],"end,":[65],"we":[66,81],"propose":[67],"GPU-NEST,":[68],"an":[69],"energy":[70,101,116],"efficiency":[71,117],"characterization":[72],"methodology":[73],"for":[74],"As":[78],"case":[79],"studies,":[80],"examined":[82],"challenges":[84],"presented":[85],"by,":[86],"implications":[88],"of,":[89],"scaling,":[91],"scheduling,":[93,120],"non-GPU":[95],"bottleneck":[96],"on":[97],"systems'":[100],"efficiency.":[102],"We":[103],"found":[104],"that":[105],"scheduling":[107],"particular":[109],"great":[111],"benefits":[112],"improving":[114],"by":[121],"much":[123],"40":[125],"percent.":[126]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":13}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}