{"id":"https://openalex.org/W4416251144","doi":"https://doi.org/10.1109/ijcnn64981.2025.11229114","title":"MOVie: GPU Memory Optimization for Large-Scale DNNs Training with Virtual Memory Management","display_name":"MOVie: GPU Memory Optimization for Large-Scale DNNs Training with Virtual Memory Management","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4416251144","doi":"https://doi.org/10.1109/ijcnn64981.2025.11229114"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11229114","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11229114","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5072733946","display_name":"Zhiyao Ma","orcid":"https://orcid.org/0000-0003-0666-8661"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zijun Ma","raw_affiliation_strings":["National University of Defense Technology,College of Computer Science and Technology,Changsha,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,College of Computer Science and Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jiabao Tang","orcid":null},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiabao Tang","raw_affiliation_strings":["National University of Defense Technology,College of Computer Science and Technology,Changsha,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,College of Computer Science and Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000084858","display_name":"Songlei Jian","orcid":"https://orcid.org/0000-0002-1435-0410"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Songlei Jian","raw_affiliation_strings":["National University of Defense Technology,College of Computer Science and Technology,Changsha,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,College of Computer Science and Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021399783","display_name":"Jianfeng Zhang","orcid":"https://orcid.org/0000-0002-4382-8700"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianfeng Zhang","raw_affiliation_strings":["National University of Defense Technology,College of Computer Science and Technology,Changsha,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,College of Computer Science and Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034435564","display_name":"Yusong Tan","orcid":"https://orcid.org/0000-0003-1233-5679"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yusong Tan","raw_affiliation_strings":["National University of Defense Technology,College of Computer Science and Technology,Changsha,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,College of Computer Science and Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.5561000108718872,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10036","display_name":"Advanced Neural Network Applications","score":0.5561000108718872,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.08619999885559082,"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":0.08340000361204147,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/memory-management","display_name":"Memory management","score":0.6639999747276306},{"id":"https://openalex.org/keywords/flat-memory-model","display_name":"Flat memory model","score":0.6402999758720398},{"id":"https://openalex.org/keywords/allocator","display_name":"Allocator","score":0.6141999959945679},{"id":"https://openalex.org/keywords/interleaved-memory","display_name":"Interleaved memory","score":0.5253999829292297},{"id":"https://openalex.org/keywords/virtual-memory","display_name":"Virtual memory","score":0.5242999792098999},{"id":"https://openalex.org/keywords/memory-map","display_name":"Memory map","score":0.48829999566078186},{"id":"https://openalex.org/keywords/extended-memory","display_name":"Extended memory","score":0.45879998803138733},{"id":"https://openalex.org/keywords/physical-address","display_name":"Physical address","score":0.4478999972343445},{"id":"https://openalex.org/keywords/c-dynamic-memory-allocation","display_name":"C dynamic memory allocation","score":0.43560001254081726},{"id":"https://openalex.org/keywords/dynamic-random-access-memory","display_name":"Dynamic random-access memory","score":0.43549999594688416}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.875},{"id":"https://openalex.org/C176649486","wikidata":"https://www.wikidata.org/wiki/Q2308807","display_name":"Memory management","level":3,"score":0.6639999747276306},{"id":"https://openalex.org/C57863822","wikidata":"https://www.wikidata.org/wiki/Q905488","display_name":"Flat memory model","level":4,"score":0.6402999758720398},{"id":"https://openalex.org/C162262903","wikidata":"https://www.wikidata.org/wiki/Q343527","display_name":"Allocator","level":2,"score":0.6141999959945679},{"id":"https://openalex.org/C63511323","wikidata":"https://www.wikidata.org/wiki/Q908936","display_name":"Interleaved memory","level":4,"score":0.5253999829292297},{"id":"https://openalex.org/C76399640","wikidata":"https://www.wikidata.org/wiki/Q189401","display_name":"Virtual memory","level":4,"score":0.5242999792098999},{"id":"https://openalex.org/C74426580","wikidata":"https://www.wikidata.org/wiki/Q719484","display_name":"Memory map","level":3,"score":0.48829999566078186},{"id":"https://openalex.org/C171675096","wikidata":"https://www.wikidata.org/wiki/Q1143380","display_name":"Extended memory","level":4,"score":0.45879998803138733},{"id":"https://openalex.org/C41036726","wikidata":"https://www.wikidata.org/wiki/Q844824","display_name":"Physical address","level":3,"score":0.4478999972343445},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.44209998846054077},{"id":"https://openalex.org/C34339311","wikidata":"https://www.wikidata.org/wiki/Q1050390","display_name":"C dynamic memory allocation","level":4,"score":0.43560001254081726},{"id":"https://openalex.org/C118702147","wikidata":"https://www.wikidata.org/wiki/Q189396","display_name":"Dynamic random-access memory","level":3,"score":0.43549999594688416},{"id":"https://openalex.org/C3720319","wikidata":"https://www.wikidata.org/wiki/Q5015937","display_name":"Cache-only memory architecture","level":5,"score":0.40470001101493835},{"id":"https://openalex.org/C51290061","wikidata":"https://www.wikidata.org/wiki/Q1936765","display_name":"Uniform memory access","level":4,"score":0.3743000030517578},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3716000020503998},{"id":"https://openalex.org/C98986596","wikidata":"https://www.wikidata.org/wiki/Q1143031","display_name":"Semiconductor memory","level":2,"score":0.3666999936103821},{"id":"https://openalex.org/C12186640","wikidata":"https://www.wikidata.org/wiki/Q6815743","display_name":"Memory model","level":3,"score":0.36000001430511475},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.35830000042915344},{"id":"https://openalex.org/C82687282","wikidata":"https://www.wikidata.org/wiki/Q66221","display_name":"Auxiliary memory","level":2,"score":0.34310001134872437},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.32409998774528503},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3125999867916107},{"id":"https://openalex.org/C39528615","wikidata":"https://www.wikidata.org/wiki/Q1229610","display_name":"Distributed shared memory","level":5,"score":0.3118000030517578},{"id":"https://openalex.org/C112049663","wikidata":"https://www.wikidata.org/wiki/Q18608","display_name":"Explicit memory","level":4,"score":0.3091999888420105},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3021000027656555},{"id":"https://openalex.org/C2781357197","wikidata":"https://www.wikidata.org/wiki/Q5757597","display_name":"High memory","level":2,"score":0.30000001192092896},{"id":"https://openalex.org/C152890283","wikidata":"https://www.wikidata.org/wiki/Q4129922","display_name":"Computing with Memory","level":5,"score":0.299699991941452},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.2957000136375427},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.29429998993873596},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.29409998655319214},{"id":"https://openalex.org/C153247305","wikidata":"https://www.wikidata.org/wiki/Q835713","display_name":"Memory address","level":3,"score":0.28049999475479126},{"id":"https://openalex.org/C93446704","wikidata":"https://www.wikidata.org/wiki/Q449328","display_name":"Registered memory","level":3,"score":0.26339998841285706},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.2621000111103058},{"id":"https://openalex.org/C86111242","wikidata":"https://www.wikidata.org/wiki/Q859595","display_name":"Coprocessor","level":2,"score":0.2612000107765198},{"id":"https://openalex.org/C25344961","wikidata":"https://www.wikidata.org/wiki/Q192726","display_name":"Virtual machine","level":2,"score":0.2599000036716461},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.25839999318122864},{"id":"https://openalex.org/C18131444","wikidata":"https://www.wikidata.org/wiki/Q163585","display_name":"Memory protection","level":5,"score":0.25529998540878296},{"id":"https://openalex.org/C34165917","wikidata":"https://www.wikidata.org/wiki/Q188267","display_name":"Programming paradigm","level":2,"score":0.2549000084400177},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2513999938964844}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11229114","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11229114","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W2489529491","https://openalex.org/W2971843695","https://openalex.org/W3012514909","https://openalex.org/W3038086838","https://openalex.org/W3081168214","https://openalex.org/W4282974189","https://openalex.org/W4282974849","https://openalex.org/W4382119135","https://openalex.org/W4394998892","https://openalex.org/W4399851470","https://openalex.org/W4404918643"],"related_works":[],"abstract_inverted_index":{"As":[0],"the":[1,6,12,28,69,77,168],"complexity":[2],"of":[3,8,16,30,72,163],"models":[4],"and":[5,97,129,157],"scale":[7],"parameters":[9],"grows":[10],"rapidly,":[11],"limited":[13],"memory":[14,44,52,57,61,66,89,109,119,126,137,151],"capacity":[15],"intelligent":[17],"acceleration":[18],"devices":[19],"such":[20],"as":[21],"GPUs":[22],"has":[23],"become":[24],"a":[25,47,107,130],"constraint":[26],"on":[27,83,117],"development":[29],"large-scale":[31,99,113,145],"deep":[32],"neural":[33],"networks":[34],"(DNNs).":[35],"Deep":[36],"learning":[37],"frameworks":[38],"employ":[39],"caching":[40],"allocators":[41],"to":[42,87,93,95,134,155,167],"manage":[43],"pools":[45],"through":[46],"\"split-merge\"":[48],"mechanism,":[49],"enhancing":[50],"GPU":[51,108,150],"utilization":[53,152],"while":[54],"inevitably":[55],"introducing":[56],"fragmentation.":[58],"While":[59],"common":[60],"optimization":[62,110],"techniques":[63],"effectively":[64],"alleviate":[65],"pressure":[67],"during":[68],"training":[70,101,115],"phase":[71],"DNNs,":[73,146],"they":[74],"also":[75],"exacerbate":[76],"fragmentation":[78],"issue.":[79],"Existing":[80],"methods":[81],"rely":[82],"pre-acquired":[84],"runtime":[85],"information":[86],"guide":[88],"allocation,":[90],"which":[91],"fails":[92],"adapt":[94],"dynamic":[96,131],"complex":[98],"DNNs":[100,114],"scenarios.":[102],"This":[103],"paper":[104],"proposes":[105],"MOVie,":[106],"method":[111],"for":[112,143],"based":[116],"virtual":[118,125],"management.":[120],"MOVie":[121,147],"utilizes":[122],"an":[123,159],"over-subscribed":[124],"merging":[127],"mechanism":[128],"programming":[132],"algorithm":[133],"combine":[135],"non-contiguous":[136],"blocks.":[138],"Experimental":[139],"results":[140],"demonstrate":[141],"that":[142],"various":[144],"can":[148],"improve":[149],"by":[153],"up":[154],"21.76%":[156],"achieves":[158],"average":[160],"performance":[161],"improvement":[162],"1.5":[164],"times":[165],"compared":[166],"state-of-the-art":[169],"methods.":[170]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-14T00:00:00"}