{"id":"https://openalex.org/W4380881153","doi":"https://doi.org/10.1145/3579371.3589059","title":"V10: Hardware-Assisted NPU Multi-tenancy for Improved Resource Utilization and Fairness","display_name":"V10: Hardware-Assisted NPU Multi-tenancy for Improved Resource Utilization and Fairness","publication_year":2023,"publication_date":"2023-06-16","ids":{"openalex":"https://openalex.org/W4380881153","doi":"https://doi.org/10.1145/3579371.3589059"},"language":"en","primary_location":{"id":"doi:10.1145/3579371.3589059","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3579371.3589059","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3579371.3589059","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 50th Annual International Symposium on Computer Architecture","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3579371.3589059","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101548931","display_name":"Yuqi Xue","orcid":"https://orcid.org/0009-0002-0363-9486"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yuqi Xue","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Urbana, Illinois, USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Urbana, Illinois, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032573239","display_name":"Yiqi Liu","orcid":"https://orcid.org/0009-0006-8171-4970"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yiqi Liu","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Urbana, Illinois, USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Urbana, Illinois, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016524466","display_name":"Lifeng Nai","orcid":"https://orcid.org/0000-0002-8801-9384"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lifeng Nai","raw_affiliation_strings":["Google, Mountain View, California, USA"],"affiliations":[{"raw_affiliation_string":"Google, Mountain View, California, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005380910","display_name":"Jian Huang","orcid":"https://orcid.org/0000-0002-1125-671X"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jian Huang","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Urbana, Illinois, USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Urbana, Illinois, USA","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101548931"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":2.3274,"has_fulltext":true,"cited_by_count":18,"citation_normalized_percentile":{"value":0.88715934,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"15"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9977999925613403,"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"}},"topics":[{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9977999925613403,"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"}},{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9976000189781189,"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":0.9976000189781189,"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":0.7668260335922241},{"id":"https://openalex.org/keywords/multitenancy","display_name":"Multitenancy","score":0.7570505142211914},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.7156307697296143},{"id":"https://openalex.org/keywords/shared-resource","display_name":"Shared resource","score":0.6134891510009766},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.542327880859375},{"id":"https://openalex.org/keywords/multiplexing","display_name":"Multiplexing","score":0.5251219868659973},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4148111045360565},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3812828063964844},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3240450918674469},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.3207947015762329},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.3195386826992035},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2918083071708679},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.18462732434272766},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.12250420451164246},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.12123438715934753},{"id":"https://openalex.org/keywords/software-as-a-service","display_name":"Software as a service","score":0.12003862857818604}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7668260335922241},{"id":"https://openalex.org/C69016650","wikidata":"https://www.wikidata.org/wiki/Q1364211","display_name":"Multitenancy","level":5,"score":0.7570505142211914},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.7156307697296143},{"id":"https://openalex.org/C51332947","wikidata":"https://www.wikidata.org/wiki/Q1172305","display_name":"Shared resource","level":2,"score":0.6134891510009766},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.542327880859375},{"id":"https://openalex.org/C19275194","wikidata":"https://www.wikidata.org/wiki/Q222903","display_name":"Multiplexing","level":2,"score":0.5251219868659973},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4148111045360565},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3812828063964844},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3240450918674469},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.3207947015762329},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.3195386826992035},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2918083071708679},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.18462732434272766},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.12250420451164246},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.12123438715934753},{"id":"https://openalex.org/C175133352","wikidata":"https://www.wikidata.org/wiki/Q1254596","display_name":"Software as a service","level":4,"score":0.12003862857818604},{"id":"https://openalex.org/C529173508","wikidata":"https://www.wikidata.org/wiki/Q638608","display_name":"Software development","level":3,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3579371.3589059","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3579371.3589059","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3579371.3589059","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 50th Annual International Symposium on Computer Architecture","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3579371.3589059","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3579371.3589059","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3579371.3589059","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 50th Annual International Symposium on Computer Architecture","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.4699999988079071,"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8"}],"awards":[{"id":"https://openalex.org/G164177236","display_name":"SPX: Collaborative Research: Scaling the Software-Defined Data Center with Network-Storage Stack Co-Design","funder_award_id":"1919044","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2083879895","display_name":null,"funder_award_id":"CNS-2144796","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2460662635","display_name":null,"funder_award_id":"2144796","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G678292349","display_name":null,"funder_award_id":"CCF-1919044","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4380881153.pdf","grobid_xml":"https://content.openalex.org/works/W4380881153.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W424435301","https://openalex.org/W2048266589","https://openalex.org/W2067523571","https://openalex.org/W2099242680","https://openalex.org/W2129381159","https://openalex.org/W2150139096","https://openalex.org/W2156077332","https://openalex.org/W2604514113","https://openalex.org/W2765927961","https://openalex.org/W2883929540","https://openalex.org/W2950656546","https://openalex.org/W2975712713","https://openalex.org/W3010835436","https://openalex.org/W3011348040","https://openalex.org/W3016939927","https://openalex.org/W3036878841","https://openalex.org/W3043406639","https://openalex.org/W3098068080","https://openalex.org/W3101026687","https://openalex.org/W3127736057","https://openalex.org/W3155057378","https://openalex.org/W3156546842","https://openalex.org/W3159535809","https://openalex.org/W4297076413"],"related_works":["https://openalex.org/W1982173150","https://openalex.org/W2100628838","https://openalex.org/W2036575706","https://openalex.org/W2071511574","https://openalex.org/W2221499367","https://openalex.org/W4244478748","https://openalex.org/W1533527424","https://openalex.org/W4223488648","https://openalex.org/W2149272485","https://openalex.org/W2094807817"],"abstract_inverted_index":{"Modern":[0],"cloud":[1],"platforms":[2],"have":[3],"deployed":[4],"neural":[5],"processing":[6],"units":[7],"(NPUs)":[8],"like":[9],"Google":[10],"Cloud":[11],"TPUs":[12],"to":[13,33,62],"accelerate":[14],"online":[15],"machine":[16],"learning":[17],"(ML)":[18],"inference":[19],"services.":[20],"To":[21],"improve":[22],"the":[23,35,63,73,88],"resource":[24,70],"utilization":[25],"of":[26,65],"NPUs,":[27],"they":[28],"allow":[29],"multiple":[30],"ML":[31],"applications":[32],"share":[34],"same":[36,89],"NPU,":[37],"and":[38,42,80],"developed":[39],"both":[40],"time-multiplexed":[41],"preemptive-based":[43],"sharing":[44,71],"mechanisms.":[45],"However,":[46],"our":[47],"study":[48],"with":[49],"real-world":[50],"NPUs":[51],"discloses":[52],"that":[53],"these":[54],"approaches":[55],"suffer":[56],"from":[57],"surprisingly":[58],"low":[59],"utilization,":[60],"due":[61],"lack":[64],"support":[66],"for":[67,96],"fine-grained":[68],"hardware":[69,94],"in":[72],"NPU.":[74],"Specifically,":[75],"its":[76],"separate":[77],"systolic":[78],"array":[79],"vector":[81],"unit":[82],"cannot":[83],"be":[84],"fully":[85],"utilized":[86],"at":[87],"time,":[90],"which":[91],"requires":[92],"fundamental":[93],"assistance":[95],"supporting":[97],"multi-tenancy.":[98]},"counts_by_year":[{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}
