{"id":"https://openalex.org/W7155352498","doi":"https://doi.org/10.1145/3777884.3797818","title":"FLYT: Transparent and Elastic GPU Provisioning for Multi-Tenant Cloud Services","display_name":"FLYT: Transparent and Elastic GPU Provisioning for Multi-Tenant Cloud Services","publication_year":2026,"publication_date":"2026-04-23","ids":{"openalex":"https://openalex.org/W7155352498","doi":"https://doi.org/10.1145/3777884.3797818"},"language":null,"primary_location":{"id":"doi:10.1145/3777884.3797818","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3777884.3797818","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM/SPEC International Conference on Performance Engineering","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3777884.3797818","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5134411220","display_name":"Santhosh M. Kumar","orcid":"https://orcid.org/0009-0006-6889-6570"},"institutions":[{"id":"https://openalex.org/I162827531","display_name":"Indian Institute of Technology Bombay","ror":"https://ror.org/02qyf5152","country_code":"IN","type":"education","lineage":["https://openalex.org/I162827531"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Santhosh M. Kumar","raw_affiliation_strings":["Indian Institute of Technology Bombay, Mumbai, India"],"raw_orcid":"https://orcid.org/0009-0006-6889-6570","affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Bombay, Mumbai, India","institution_ids":["https://openalex.org/I162827531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134414809","display_name":"Sameer Ahmad","orcid":"https://orcid.org/0000-0002-6029-0156"},"institutions":[{"id":"https://openalex.org/I162827531","display_name":"Indian Institute of Technology Bombay","ror":"https://ror.org/02qyf5152","country_code":"IN","type":"education","lineage":["https://openalex.org/I162827531"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sameer Ahmad","raw_affiliation_strings":["Indian Institute of Technology Bombay, Mumbai, India"],"raw_orcid":"https://orcid.org/0000-0002-6029-0156","affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Bombay, Mumbai, India","institution_ids":["https://openalex.org/I162827531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5099843832","display_name":"Armaan Chowfin","orcid":"https://orcid.org/0009-0000-6543-1037"},"institutions":[{"id":"https://openalex.org/I162827531","display_name":"Indian Institute of Technology Bombay","ror":"https://ror.org/02qyf5152","country_code":"IN","type":"education","lineage":["https://openalex.org/I162827531"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Armaan Chowfin","raw_affiliation_strings":["Indian Institute of Technology, Mumbai, India"],"raw_orcid":"https://orcid.org/0009-0000-6543-1037","affiliations":[{"raw_affiliation_string":"Indian Institute of Technology, Mumbai, India","institution_ids":["https://openalex.org/I162827531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111441567","display_name":"Purushottam Kulkarni","orcid":null},"institutions":[{"id":"https://openalex.org/I162827531","display_name":"Indian Institute of Technology Bombay","ror":"https://ror.org/02qyf5152","country_code":"IN","type":"education","lineage":["https://openalex.org/I162827531"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Purushottam Kulkarni","raw_affiliation_strings":["Indian Institute of Technology, Mumbai, India"],"raw_orcid":"https://orcid.org/0009-0008-0272-9299","affiliations":[{"raw_affiliation_string":"Indian Institute of Technology, Mumbai, India","institution_ids":["https://openalex.org/I162827531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009613449","display_name":"Anand Eswaran","orcid":null},"institutions":[{"id":"https://openalex.org/I4210103279","display_name":"IBM Research - India","ror":"https://ror.org/014wt7r80","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210103279","https://openalex.org/I4210114115"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Anand Eswaran","raw_affiliation_strings":["IBM Research, Bangalore, India"],"raw_orcid":"https://orcid.org/0009-0004-2189-555X","affiliations":[{"raw_affiliation_string":"IBM Research, Bangalore, India","institution_ids":["https://openalex.org/I4210103279"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019646943","display_name":"Praveen Jayachandran","orcid":"https://orcid.org/0000-0001-8961-9990"},"institutions":[{"id":"https://openalex.org/I4210103279","display_name":"IBM Research - India","ror":"https://ror.org/014wt7r80","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210103279","https://openalex.org/I4210114115"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Praveen Jayachandran","raw_affiliation_strings":["IBM Research, Bangalore, India"],"raw_orcid":"https://orcid.org/0000-0001-8961-9990","affiliations":[{"raw_affiliation_string":"IBM Research, Bangalore, India","institution_ids":["https://openalex.org/I4210103279"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5134411220"],"corresponding_institution_ids":["https://openalex.org/I162827531"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.966473,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"325","last_page":"332"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.661899983882904,"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":0.661899983882904,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.12890000641345978,"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/T14347","display_name":"Big Data and Digital Economy","score":0.0340999998152256,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.8208000063896179},{"id":"https://openalex.org/keywords/provisioning","display_name":"Provisioning","score":0.7422000169754028},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.47269999980926514},{"id":"https://openalex.org/keywords/virtualization","display_name":"Virtualization","score":0.4708000123500824},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.45980000495910645},{"id":"https://openalex.org/keywords/live-migration","display_name":"Live migration","score":0.4163999855518341},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.40139999985694885},{"id":"https://openalex.org/keywords/multiplexing","display_name":"Multiplexing","score":0.38850000500679016}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8546000123023987},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.8208000063896179},{"id":"https://openalex.org/C172191483","wikidata":"https://www.wikidata.org/wiki/Q1071806","display_name":"Provisioning","level":2,"score":0.7422000169754028},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4925000071525574},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.47269999980926514},{"id":"https://openalex.org/C513985346","wikidata":"https://www.wikidata.org/wiki/Q270471","display_name":"Virtualization","level":3,"score":0.4708000123500824},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.45980000495910645},{"id":"https://openalex.org/C2778710394","wikidata":"https://www.wikidata.org/wiki/Q4179813","display_name":"Live migration","level":4,"score":0.4163999855518341},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.40139999985694885},{"id":"https://openalex.org/C19275194","wikidata":"https://www.wikidata.org/wiki/Q222903","display_name":"Multiplexing","level":2,"score":0.38850000500679016},{"id":"https://openalex.org/C121854251","wikidata":"https://www.wikidata.org/wiki/Q62932","display_name":"Elasticity (physics)","level":2,"score":0.38769999146461487},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3853999972343445},{"id":"https://openalex.org/C199168358","wikidata":"https://www.wikidata.org/wiki/Q3367000","display_name":"Orchestration","level":3,"score":0.36730000376701355},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3409000039100647},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.320499986410141},{"id":"https://openalex.org/C25344961","wikidata":"https://www.wikidata.org/wiki/Q192726","display_name":"Virtual machine","level":2,"score":0.31540000438690186},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.30300000309944153},{"id":"https://openalex.org/C47487241","wikidata":"https://www.wikidata.org/wiki/Q5227230","display_name":"Data access","level":2,"score":0.30250000953674316},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.2937000095844269},{"id":"https://openalex.org/C2983523559","wikidata":"https://www.wikidata.org/wiki/Q410657","display_name":"On demand","level":2,"score":0.2743000090122223},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.26820001006126404},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.2563000023365021},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.25519999861717224},{"id":"https://openalex.org/C2780378061","wikidata":"https://www.wikidata.org/wiki/Q25351891","display_name":"Service (business)","level":2,"score":0.2547999918460846}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3777884.3797818","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3777884.3797818","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM/SPEC International Conference on Performance Engineering","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3777884.3797818","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3777884.3797818","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM/SPEC International Conference on Performance Engineering","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1996212904","https://openalex.org/W2005574683","https://openalex.org/W2194775991","https://openalex.org/W2963446712","https://openalex.org/W3003455055","https://openalex.org/W3180530691","https://openalex.org/W4281384434","https://openalex.org/W4381885923","https://openalex.org/W4388153979","https://openalex.org/W4394944658"],"related_works":[],"abstract_inverted_index":{"Modern":[0],"cloud":[1,66],"services":[2],"such":[3],"as":[4],"AI":[5],"inference,":[6],"video":[7],"analytics,":[8],"and":[9,15,23,38,77,101,119],"scientific":[10],"computing":[11],"exhibit":[12],"highly":[13],"variable":[14],"bursty":[16],"GPU":[17,32,61,104,114],"demand":[18],"patterns":[19],"that":[20],"static":[21],"provisioning":[22],"coarse-grained":[24],"sharing":[25],"mechanism":[26],"struggle":[27],"to":[28,48,89],"accommodate":[29],"efficiently.":[30],"Existing":[31],"multiplexing":[33],"approaches,":[34],"including":[35],"NVIDIA":[36],"MPS":[37],"MIG,":[39],"provide":[40],"limited":[41],"flexibility":[42],"in":[43],"multi-tenant":[44],"environments,":[45],"often":[46],"leading":[47],"resource":[49],"fragmentation,":[50],"under-utilization,":[51],"or":[52,108],"unpredictable":[53],"latency.":[54],"We":[55],"present":[56],"Flyt,":[57],"a":[58,87],"transparent,":[59],"latency-0aware":[60],"orchestration":[62],"framework":[63],"for":[64],"virtualized":[65],"services.":[67],"Flyt":[68],"enables":[69],"fine-grain":[70],"runtime":[71],"scaling":[72,100],"of":[73],"Streaming":[74],"Multiprocessors":[75],"(SMs)":[76],"breaks":[78],"the":[79],"traditional":[80],"VM\u2013GPUs":[81],"binding":[82],"by":[83,112],"allowing":[84],"applications":[85],"inside":[86],"VM":[88],"execute":[90],"on":[91],"different":[92],"GPUs":[93],"over":[94],"time.":[95],"This":[96],"design":[97],"supports":[98],"elastic":[99,121],"live":[102],"inter\u2013node":[103],"migration":[105],"without":[106],"application":[107],"guest":[109],"OS":[110],"modifications,":[111],"virtualizing":[113],"memory":[115],"through":[116],"address":[117],"translation":[118],"enforcing":[120],"SM":[122],"execution":[123],"caps.":[124]},"counts_by_year":[],"updated_date":"2026-04-24T06:07:52.864757","created_date":"2026-04-24T00:00:00"}
