{"id":"https://openalex.org/W4410886897","doi":"https://doi.org/10.1109/mm.2025.3574630","title":"Hardware-Assisted Virtualization of Neural Processing Units for Cloud Platforms","display_name":"Hardware-Assisted Virtualization of Neural Processing Units for Cloud Platforms","publication_year":2025,"publication_date":"2025-05-30","ids":{"openalex":"https://openalex.org/W4410886897","doi":"https://doi.org/10.1109/mm.2025.3574630"},"language":"en","primary_location":{"id":"doi:10.1109/mm.2025.3574630","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mm.2025.3574630","pdf_url":null,"source":{"id":"https://openalex.org/S59697426","display_name":"IEEE Micro","issn_l":"0272-1732","issn":["0272-1732","1937-4143"],"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 Micro","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/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 Urbana-Champaign, Urbana, IL, USA"],"raw_orcid":"https://orcid.org/0009-0002-0363-9486","affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign, Urbana, IL, 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 Urbana-Champaign, Urbana, IL, USA"],"raw_orcid":"https://orcid.org/0009-0006-8171-4970","affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign, Urbana, IL, 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 Inc., Mountain View, CA, USA","Google, Mountain View, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-8801-9384","affiliations":[{"raw_affiliation_string":"Google Inc., Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google, Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":null,"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 Urbana-Champaign, Urbana, IL, USA"],"raw_orcid":"https://orcid.org/0000-0002-1125-671X","affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign, Urbana, IL, 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":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.05400978,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"45","issue":"4","first_page":"29","last_page":"36"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.9257000088691711,"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"}},"topics":[{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.9257000088691711,"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/computer-science","display_name":"Computer science","score":0.843227207660675},{"id":"https://openalex.org/keywords/virtualization","display_name":"Virtualization","score":0.741207480430603},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.7263025641441345},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.5946940183639526},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.507206916809082},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.4510570764541626},{"id":"https://openalex.org/keywords/full-virtualization","display_name":"Full virtualization","score":0.42561620473861694},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.32052257657051086}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.843227207660675},{"id":"https://openalex.org/C513985346","wikidata":"https://www.wikidata.org/wiki/Q270471","display_name":"Virtualization","level":3,"score":0.741207480430603},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.7263025641441345},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.5946940183639526},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.507206916809082},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.4510570764541626},{"id":"https://openalex.org/C47878483","wikidata":"https://www.wikidata.org/wiki/Q848333","display_name":"Full virtualization","level":4,"score":0.42561620473861694},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.32052257657051086}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mm.2025.3574630","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mm.2025.3574630","pdf_url":null,"source":{"id":"https://openalex.org/S59697426","display_name":"IEEE Micro","issn_l":"0272-1732","issn":["0272-1732","1937-4143"],"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 Micro","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"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/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":false,"pdf":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W3016939927","https://openalex.org/W3043571714","https://openalex.org/W4380881153","https://openalex.org/W4381611549","https://openalex.org/W4404954356"],"related_works":["https://openalex.org/W2134071009","https://openalex.org/W2021257679","https://openalex.org/W2067755938","https://openalex.org/W633976324","https://openalex.org/W2106040863","https://openalex.org/W2934008251","https://openalex.org/W165920943","https://openalex.org/W190436017","https://openalex.org/W2019379525","https://openalex.org/W2554427106"],"abstract_inverted_index":{"Cloud":[0],"platforms":[1],"have":[2],"deployed":[3],"hardware":[4],"accelerators":[5],"like":[6],"neural":[7],"processing":[8],"units":[9,98],"(NPUs)":[10],"for":[11,33,37,58,72,91,125,130],"machine":[12],"learning":[13],"(ML)":[14],"inference":[15],"services.":[16,40],"To":[17],"maximize":[18],"resource":[19,35],"utilization":[20],"while":[21],"ensuring":[22],"quality":[23],"of":[24,54,67,85,94,121],"service,":[25],"a":[26,100,105,137],"natural":[27],"approach":[28],"is":[29,44,47],"to":[30,51,64,140],"virtualize":[31],"NPUs":[32,43],"efficient":[34],"sharing":[36,147],"multi-tenant":[38],"ML":[39],"However,":[41],"virtualizing":[42],"challenging.":[45],"This":[46,76],"not":[48],"only":[49],"due":[50,63],"the":[52,65,95],"lack":[53,66],"system":[55],"abstraction":[56,88],"support":[57,71],"NPU":[59,81,102,123,146],"hardware,":[60],"but":[61],"also":[62],"architectural":[68],"and":[69,112,116],"ISA":[70,119],"fine-grained":[73,92,126],"operator":[74,128],"scheduling.":[75],"article":[77],"presents":[78],"Neu10,":[79],"an":[80,87,118],"virtualization":[82,93],"framework":[83],"consisting":[84],"(1)":[86],"called":[89],"vNPU":[90,106],"heterogeneous":[96],"compute":[97],"in":[99],"physical":[101],"(pNPU);":[103],"(2)":[104],"allocator":[107],"that":[108],"enables":[109],"pay-as-you-go":[110],"pricing":[111],"flexible":[113],"vNPU-to-pNPU":[114],"mappings;":[115],"(3)":[117],"extension":[120],"modern":[122],"architecture":[124],"tensor":[127],"scheduling":[129],"multiple":[131],"vNPUs.":[132],"We":[133],"evaluate":[134],"Neu10":[135],"with":[136],"production-level":[138],"simulator":[139],"demonstrate":[141],"its":[142],"benefits":[143],"over":[144],"state-of-the-art":[145],"approaches.":[148]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
