{"id":"https://openalex.org/W7125803851","doi":"https://doi.org/10.1109/tcc.2026.3658199","title":"Fragmentation-Aware and Efficiency-Oriented Scheduling for GPU Sharing Workloads","display_name":"Fragmentation-Aware and Efficiency-Oriented Scheduling for GPU Sharing Workloads","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7125803851","doi":"https://doi.org/10.1109/tcc.2026.3658199"},"language":null,"primary_location":{"id":"doi:10.1109/tcc.2026.3658199","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcc.2026.3658199","pdf_url":null,"source":{"id":"https://openalex.org/S2492498579","display_name":"IEEE Transactions on Cloud Computing","issn_l":"2168-7161","issn":["2168-7161","2372-0018"],"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 Transactions on Cloud Computing","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/A5124015399","display_name":"Delai Deng","orcid":null},"institutions":[{"id":"https://openalex.org/I173899330","display_name":"Henan University","ror":"https://ror.org/003xyzq10","country_code":"CN","type":"education","lineage":["https://openalex.org/I173899330"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Delai Deng","raw_affiliation_strings":["School of Computer and Information Engineering, Henan University, Kaifeng, China"],"affiliations":[{"raw_affiliation_string":"School of Computer and Information Engineering, Henan University, Kaifeng, China","institution_ids":["https://openalex.org/I173899330"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123982104","display_name":"Yuxiang Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I173899330","display_name":"Henan University","ror":"https://ror.org/003xyzq10","country_code":"CN","type":"education","lineage":["https://openalex.org/I173899330"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuxiang Ma","raw_affiliation_strings":["School of Computer and Information Engineering, Henan University, Kaifeng, China"],"affiliations":[{"raw_affiliation_string":"School of Computer and Information Engineering, Henan University, Kaifeng, China","institution_ids":["https://openalex.org/I173899330"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123938261","display_name":"Yulei Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I36234482","display_name":"University of Bristol","ror":"https://ror.org/0524sp257","country_code":"GB","type":"education","lineage":["https://openalex.org/I36234482"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yulei Wu","raw_affiliation_strings":["School of Electrical, Electronic and Mechanical Engineering, University of Bristol, Bristol, U.K"],"affiliations":[{"raw_affiliation_string":"School of Electrical, Electronic and Mechanical Engineering, University of Bristol, Bristol, U.K","institution_ids":["https://openalex.org/I36234482"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5123964779","display_name":"Huijie Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I173899330","display_name":"Henan University","ror":"https://ror.org/003xyzq10","country_code":"CN","type":"education","lineage":["https://openalex.org/I173899330"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huijie Ma","raw_affiliation_strings":["School of Computer and Information Engineering, Henan University, Kaifeng, China"],"affiliations":[{"raw_affiliation_string":"School of Computer and Information Engineering, Henan University, Kaifeng, China","institution_ids":["https://openalex.org/I173899330"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5124015399"],"corresponding_institution_ids":["https://openalex.org/I173899330"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.226451,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"14","issue":"1","first_page":"242","last_page":"258"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.4401000142097473,"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"}},"topics":[{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.4401000142097473,"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":0.16429999470710754,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.10360000282526016,"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/scheduling","display_name":"Scheduling (production processes)","score":0.6212999820709229},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.5845000147819519},{"id":"https://openalex.org/keywords/particle-swarm-optimization","display_name":"Particle swarm optimization","score":0.4702000021934509},{"id":"https://openalex.org/keywords/job-shop-scheduling","display_name":"Job shop scheduling","score":0.3977999985218048},{"id":"https://openalex.org/keywords/execution-time","display_name":"Execution time","score":0.3896999955177307},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.3691999912261963},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.3452000021934509},{"id":"https://openalex.org/keywords/fragmentation","display_name":"Fragmentation (computing)","score":0.3416999876499176}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8711000084877014},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.6212999820709229},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.5845000147819519},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.47189998626708984},{"id":"https://openalex.org/C85617194","wikidata":"https://www.wikidata.org/wiki/Q2072794","display_name":"Particle swarm optimization","level":2,"score":0.4702000021934509},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4032000005245209},{"id":"https://openalex.org/C55416958","wikidata":"https://www.wikidata.org/wiki/Q6206757","display_name":"Job shop scheduling","level":3,"score":0.3977999985218048},{"id":"https://openalex.org/C2989134064","wikidata":"https://www.wikidata.org/wiki/Q288510","display_name":"Execution time","level":2,"score":0.3896999955177307},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3691999912261963},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3452000021934509},{"id":"https://openalex.org/C191015642","wikidata":"https://www.wikidata.org/wiki/Q1132459","display_name":"Fragmentation (computing)","level":2,"score":0.3416999876499176},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3294000029563904},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.32670000195503235},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.3050000071525574},{"id":"https://openalex.org/C106516650","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm design","level":2,"score":0.2985000014305115},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2791999876499176},{"id":"https://openalex.org/C172430144","wikidata":"https://www.wikidata.org/wiki/Q17111997","display_name":"Symmetric multiprocessor system","level":2,"score":0.27639999985694885},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.2727000117301941},{"id":"https://openalex.org/C2780898871","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Performance metric","level":2,"score":0.2720000147819519},{"id":"https://openalex.org/C107568181","wikidata":"https://www.wikidata.org/wiki/Q5319000","display_name":"Dynamic priority scheduling","level":3,"score":0.27129998803138733},{"id":"https://openalex.org/C51332947","wikidata":"https://www.wikidata.org/wiki/Q1172305","display_name":"Shared resource","level":2,"score":0.26109999418258667},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.26089999079704285},{"id":"https://openalex.org/C2984822820","wikidata":"https://www.wikidata.org/wiki/Q1123036","display_name":"Processor scheduling","level":3,"score":0.25380000472068787}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcc.2026.3658199","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcc.2026.3658199","pdf_url":null,"source":{"id":"https://openalex.org/S2492498579","display_name":"IEEE Transactions on Cloud Computing","issn_l":"2168-7161","issn":["2168-7161","2372-0018"],"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 Transactions on Cloud Computing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1996212904","https://openalex.org/W2070192642","https://openalex.org/W2141992894","https://openalex.org/W2798515322","https://openalex.org/W2922785423","https://openalex.org/W2950683227","https://openalex.org/W3022548332","https://openalex.org/W3035240825","https://openalex.org/W3089096050","https://openalex.org/W3133138424","https://openalex.org/W3162118826","https://openalex.org/W3178367256","https://openalex.org/W3209503812","https://openalex.org/W4225662012","https://openalex.org/W4290991121","https://openalex.org/W4319068657","https://openalex.org/W4372262787","https://openalex.org/W4383899813","https://openalex.org/W4392309097","https://openalex.org/W4395020669","https://openalex.org/W4400410044","https://openalex.org/W4404385885","https://openalex.org/W4408117163","https://openalex.org/W4408182811"],"related_works":[],"abstract_inverted_index":{"The":[0],"rapid":[1],"development":[2],"of":[3],"Artificial":[4],"Intelligence":[5],"(AI)":[6],"has":[7],"increased":[8],"the":[9,147,162,172,176,185],"demand":[10],"for":[11],"GPU":[12,28,58,91,106,120,133,177],"resources,":[13],"leading":[14],"to":[15,39,145,160,181,190],"a":[16,26,80,98,110,127,141,154],"surge":[17],"in":[18,30],"deep":[19,41],"learning":[20,42],"tasks":[21,43],"on":[22,166],"heterogeneous":[23,123],"GPUs.":[24],"As":[25],"result,":[27],"resources":[29],"production":[31,168],"clusters":[32],"are":[33,60],"often":[34,66],"limited.":[35],"It":[36],"is":[37],"essential":[38],"execute":[40],"efficiently":[44],"within":[45],"these":[46,64],"resource":[47],"and":[48,56,68,86,93,105,119,135,183],"time":[49,54],"constraints.":[50],"Reducing":[51],"task":[52,117,136],"completion":[53],"(TCT)":[55],"improving":[57],"utilization":[59,92,178],"both":[61,116],"critical.":[62],"However,":[63],"goals":[65],"conflict,":[67],"existing":[69,193],"solutions":[70],"remain":[71],"basic,":[72],"making":[73],"joint":[74],"optimization":[75],"challenging.":[76],"We":[77,108,138,151],"propose":[78],"BFE,":[79],"method":[81],"that":[82,101,114,130,171],"integrates":[83],"fragmentation":[84,112],"awareness":[85],"efficiency":[87,134],"orientation.":[88],"BFE":[89,174],"improves":[90,175],"reduces":[94,184],"TCT":[95,104,187],"by":[96,179,188],"utilizing":[97],"cost":[99],"model":[100],"combines":[102],"average":[103,186],"fragmentation.":[107],"introduce":[109],"new":[111],"metric":[113],"considers":[115],"size":[118],"heterogeneity.":[121],"For":[122],"environments,":[124],"we":[125],"present":[126,140],"mathematical":[128],"formulation":[129],"further":[131],"enhances":[132],"scheduling.":[137],"also":[139],"sliding":[142],"window-based":[143],"strategy":[144],"support":[146],"online":[148],"scheduling":[149,158],"scenario.":[150],"then":[152],"design":[153],"particle":[155],"swarm":[156],"optimization-based":[157],"algorithm":[159],"minimize":[161],"combined":[163],"cost.":[164],"Experiments":[165],"Alibaba's":[167],"traces":[169],"demonstrate":[170],"proposed":[173],"up":[180,189],"51.73%":[182],"55.16%,":[191],"outperforming":[192],"methods.":[194]},"counts_by_year":[],"updated_date":"2026-03-12T06:13:28.667946","created_date":"2026-01-28T00:00:00"}