{"id":"https://openalex.org/W4416922919","doi":"https://doi.org/10.1109/ton.2025.3635222","title":"Resource-Aware Distributed Training Job Placement for GPU Cluster Defragmentation","display_name":"Resource-Aware Distributed Training Job Placement for GPU Cluster Defragmentation","publication_year":2025,"publication_date":"2025-12-02","ids":{"openalex":"https://openalex.org/W4416922919","doi":"https://doi.org/10.1109/ton.2025.3635222"},"language":null,"primary_location":{"id":"doi:10.1109/ton.2025.3635222","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ton.2025.3635222","pdf_url":null,"source":{"id":"https://openalex.org/S5407042750","display_name":"IEEE Transactions on Networking","issn_l":"2998-4157","issn":["2998-4157"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Networking","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/A5074187380","display_name":"Gongming Zhao","orcid":"https://orcid.org/0000-0003-1311-8908"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gongming Zhao","raw_affiliation_strings":["School of Computer Science and Technology, University of Science and Technology of China, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0000-0003-1311-8908","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yichen Dong","orcid":"https://orcid.org/0009-0005-8312-8409"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yichen Dong","raw_affiliation_strings":["School of Computer Science and Technology, University of Science and Technology of China, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0009-0005-8312-8409","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063184427","display_name":"Hongli Xu","orcid":"https://orcid.org/0000-0003-3831-4577"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongli Xu","raw_affiliation_strings":["School of Computer Science and Technology, University of Science and Technology of China, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0000-0003-3831-4577","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010510283","display_name":"J. H. Fang","orcid":"https://orcid.org/0000-0003-4222-1971"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jin Fang","raw_affiliation_strings":["School of Computer Science and Technology, University of Science and Technology of China, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0000-0003-4222-1971","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069116683","display_name":"Zhen Yao","orcid":"https://orcid.org/0000-0001-8369-843X"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhen Yao","raw_affiliation_strings":["Huawei Technologies Company Ltd., Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Technologies Company Ltd., Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014723072","display_name":"Baoyi An","orcid":"https://orcid.org/0000-0001-9471-5223"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Baoyi An","raw_affiliation_strings":["Huawei Technologies Company Ltd., Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0001-9471-5223","affiliations":[{"raw_affiliation_string":"Huawei Technologies Company Ltd., Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004257623","display_name":"Gangyi Luo","orcid":"https://orcid.org/0009-0007-7329-5291"},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gangyi Luo","raw_affiliation_strings":["China Mobile (Suzhou) Software Technology Company Ltd., Suzhou, Jiangsu, China"],"raw_orcid":"https://orcid.org/0009-0007-7329-5291","affiliations":[{"raw_affiliation_string":"China Mobile (Suzhou) Software Technology Company Ltd., Suzhou, Jiangsu, China","institution_ids":["https://openalex.org/I180662265"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007959870","display_name":"Xu Chu","orcid":"https://orcid.org/0000-0002-6816-1076"},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chu Xu","raw_affiliation_strings":["China Mobile (Suzhou) Software Technology Company Ltd., Suzhou, Jiangsu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Mobile (Suzhou) Software Technology Company Ltd., Suzhou, Jiangsu, China","institution_ids":["https://openalex.org/I180662265"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.47181272,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"34","issue":null,"first_page":"1865","last_page":"1881"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.35120001435279846,"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":0.35120001435279846,"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":0.1615999937057495,"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/T14347","display_name":"Big Data and Digital Economy","score":0.09269999712705612,"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":0.7565000057220459},{"id":"https://openalex.org/keywords/server","display_name":"Server","score":0.6175000071525574},{"id":"https://openalex.org/keywords/testbed","display_name":"Testbed","score":0.5432999730110168},{"id":"https://openalex.org/keywords/idle","display_name":"Idle","score":0.535099983215332},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.5116999745368958},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.42500001192092896},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.41690000891685486},{"id":"https://openalex.org/keywords/cluster","display_name":"Cluster (spacecraft)","score":0.41290000081062317}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8069000244140625},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.7565000057220459},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.6175000071525574},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.6003000140190125},{"id":"https://openalex.org/C31395832","wikidata":"https://www.wikidata.org/wiki/Q1318674","display_name":"Testbed","level":2,"score":0.5432999730110168},{"id":"https://openalex.org/C16320812","wikidata":"https://www.wikidata.org/wiki/Q1812200","display_name":"Idle","level":2,"score":0.535099983215332},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.5116999745368958},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.42500001192092896},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.41690000891685486},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.41290000081062317},{"id":"https://openalex.org/C51823790","wikidata":"https://www.wikidata.org/wiki/Q504353","display_name":"Greedy algorithm","level":2,"score":0.3930000066757202},{"id":"https://openalex.org/C2992911641","wikidata":"https://www.wikidata.org/wiki/Q261362","display_name":"Job placement","level":3,"score":0.3560999929904938},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.3255000114440918},{"id":"https://openalex.org/C29140674","wikidata":"https://www.wikidata.org/wiki/Q206637","display_name":"Computer cluster","level":2,"score":0.31299999356269836},{"id":"https://openalex.org/C2781335571","wikidata":"https://www.wikidata.org/wiki/Q2633544","display_name":"GPU cluster","level":3,"score":0.3068000078201294},{"id":"https://openalex.org/C191015642","wikidata":"https://www.wikidata.org/wiki/Q1132459","display_name":"Fragmentation (computing)","level":2,"score":0.30489999055862427},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.2881999909877777},{"id":"https://openalex.org/C111873713","wikidata":"https://www.wikidata.org/wiki/Q1641413","display_name":"Job scheduler","level":3,"score":0.27869999408721924},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.25699999928474426},{"id":"https://openalex.org/C55416958","wikidata":"https://www.wikidata.org/wiki/Q6206757","display_name":"Job shop scheduling","level":3,"score":0.2558000087738037},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.2506999969482422}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ton.2025.3635222","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ton.2025.3635222","pdf_url":null,"source":{"id":"https://openalex.org/S5407042750","display_name":"IEEE Transactions on Networking","issn_l":"2998-4157","issn":["2998-4157"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Networking","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1458367098","display_name":null,"funder_award_id":"62372426","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G247584509","display_name":null,"funder_award_id":"2023481","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G645416012","display_name":null,"funder_award_id":"62132019","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1997783781","https://openalex.org/W2000444555","https://openalex.org/W2118382442","https://openalex.org/W2130531694","https://openalex.org/W2194775991","https://openalex.org/W2500139799","https://openalex.org/W2896457183","https://openalex.org/W2951947775","https://openalex.org/W3010528756","https://openalex.org/W3016395792","https://openalex.org/W3036703963","https://openalex.org/W3042185737","https://openalex.org/W3047610867","https://openalex.org/W3152632047","https://openalex.org/W3154431492","https://openalex.org/W3175449831","https://openalex.org/W4221008227","https://openalex.org/W4224926627","https://openalex.org/W4283211930","https://openalex.org/W4289401659","https://openalex.org/W4290991121","https://openalex.org/W4312864291","https://openalex.org/W4318541537","https://openalex.org/W4321484191","https://openalex.org/W4372262787","https://openalex.org/W4383620346","https://openalex.org/W4386230822","https://openalex.org/W4388966802","https://openalex.org/W4401176820"],"related_works":[],"abstract_inverted_index":{"Distributed":[0],"training":[1,16,94,154,245],"(DT)":[2],"has":[3],"emerged":[4],"as":[5,60,64],"a":[6,76,111,137,164,191,212,220],"solution":[7],"to":[8,31,42,66,75,145,257],"address":[9],"the":[10,84,89,118,125,249,252,258],"growing":[11],"computational":[12],"resource":[13,85,121,133],"demands":[14],"of":[15,88,120,127,152,224,251],"large-scale":[17,153,213],"machine":[18],"learning":[19],"models.":[20],"To":[21,130,173],"meet":[22],"this":[23,71,100,175],"need,":[24],"cloud":[25,39,97],"providers":[26,40],"typically":[27],"build":[28],"GPU":[29,90,147],"clusters":[30],"accommodate":[32],"DT":[33,36],"jobs.":[34,155],"For":[35],"job":[37,52,113,217],"requests,":[38],"need":[41],"determine":[43],"in":[44],"which":[45,82],"GPUs":[46],"place":[47,57],"workers":[48,58],"(<italic":[49],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[50,78,105,157,178,196,205,236],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">i.e.</i>,":[51],"placement).":[53],"Existing":[54],"approaches":[55],"usually":[56],"on":[59],"few":[61],"idle":[62],"machines":[63],"possible":[65],"minimize":[67],"communication":[68],"time.":[69],"However,":[70],"scheme":[72,115],"will":[73],"lead":[74],"<italic":[77],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">resource":[79],"fragmentation":[80,122],"problem</i>,":[81],"degrades":[83],"utilization":[86,126],"rate":[87],"cluster":[91,253],"and":[92,169,219],"increases":[93],"costs":[95],"for":[96],"providers.":[98],"In":[99],"paper,":[101],"we":[102,135],"propose":[103],"<inline-formula":[104,156,177,204,235],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">":[106,158,179,197,206,237],"<tex-math":[107,159,180,198,207,238],"notation=\"LaTeX\">$\\textsf":[108,160,181,208,239],"{Titan}$</tex-math>":[109,161,182,209,240],"</inline-formula>,":[110],"novel":[112],"placement":[114,151],"that":[116,141,234],"mitigates":[117],"influence":[119],"by":[123,254],"enhancing":[124],"non-idle":[128],"machines.":[129],"further":[131],"optimize":[132],"allocation,":[134],"introduce":[136],"dynamic":[138],"defragmentation":[139],"algorithm":[140,189],"migrates":[142],"fragmented":[143],"jobs":[144],"consolidate":[146],"resources,":[148],"enabling":[149],"efficient":[150],"</inline-formula>":[162,183,210,241],"formulates":[163],"multi-objective":[165],"non-linear":[166],"optimization":[167],"problem":[168],"proves":[170],"its":[171],"NP-hardness.":[172],"solve":[174],"problem,":[176],"presents":[184],"an":[185],"effective":[186],"submodular-based":[187],"greedy":[188],"with":[190,211,227],"tight":[192],"approximation":[193],"ratio":[194],"(<inline-formula":[195],"notation=\"LaTeX\">$1-\\frac":[199],"{1}{e}$</tex-math>":[200],"</inline-formula>).":[201],"We":[202],"evaluate":[203],"simulation":[214],"employing":[215],"real-world":[216],"traces":[218],"small-scale":[221],"testbed":[222],"consisting":[223],"8":[225],"servers":[226],"32":[228],"logical":[229],"GPUs.":[230],"Experimental":[231],"results":[232],"show":[233],"can":[242],"achieve":[243],"near-optimal":[244],"throughput":[246],"while":[247],"improving":[248],"efficiency":[250],"74.9%":[255],"compared":[256],"state-of-the-art":[259],"solutions.":[260]},"counts_by_year":[],"updated_date":"2026-01-10T23:39:48.068659","created_date":"2025-12-02T00:00:00"}