{"id":"https://openalex.org/W4411584676","doi":"https://doi.org/10.1109/msn63567.2024.00102","title":"DOME: Dynamic Optimization of GPU Memory for Training DNN Models with Limited Resources","display_name":"DOME: Dynamic Optimization of GPU Memory for Training DNN Models with Limited Resources","publication_year":2024,"publication_date":"2024-12-20","ids":{"openalex":"https://openalex.org/W4411584676","doi":"https://doi.org/10.1109/msn63567.2024.00102"},"language":"en","primary_location":{"id":"doi:10.1109/msn63567.2024.00102","is_oa":false,"landing_page_url":"https://doi.org/10.1109/msn63567.2024.00102","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 20th International Conference on Mobility, Sensing and Networking (MSN)","raw_type":"proceedings-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/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":true,"raw_author_name":"Zijun Ma","raw_affiliation_strings":["College of Computer Science and Technology, National University of Defense Technology,Changsha,China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, National University of Defense 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":["College of Computer Science and Technology, National University of Defense Technology,Changsha,China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, National University of Defense 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":["College of Computer Science and Technology, National University of Defense Technology,Changsha,China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, National University of Defense Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5072733946"],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.33759886,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"722","last_page":"729"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12702","display_name":"Brain Tumor Detection and Classification","score":0.9354000091552734,"subfield":{"id":"https://openalex.org/subfields/2808","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T12702","display_name":"Brain Tumor Detection and Classification","score":0.9354000091552734,"subfield":{"id":"https://openalex.org/subfields/2808","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9340999722480774,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7946560382843018},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.6657839417457581},{"id":"https://openalex.org/keywords/dome","display_name":"Dome (geology)","score":0.593016505241394},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5372118353843689},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.32821857929229736},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32077229022979736},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.3205454349517822},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.14177188277244568}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7946560382843018},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.6657839417457581},{"id":"https://openalex.org/C189092281","wikidata":"https://www.wikidata.org/wiki/Q3236743","display_name":"Dome (geology)","level":2,"score":0.593016505241394},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5372118353843689},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.32821857929229736},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32077229022979736},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.3205454349517822},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.14177188277244568},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/msn63567.2024.00102","is_oa":false,"landing_page_url":"https://doi.org/10.1109/msn63567.2024.00102","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 20th International Conference on Mobility, Sensing and Networking (MSN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1978690967","https://openalex.org/W2489529491","https://openalex.org/W2997768846","https://openalex.org/W3012479151","https://openalex.org/W3012514909","https://openalex.org/W3034719990","https://openalex.org/W3086105743","https://openalex.org/W3170887803","https://openalex.org/W3205803342","https://openalex.org/W4285148475","https://openalex.org/W4288059664","https://openalex.org/W4289533987","https://openalex.org/W4301361180","https://openalex.org/W4321636583","https://openalex.org/W4364322902","https://openalex.org/W4384705429","https://openalex.org/W4388116617","https://openalex.org/W4393145114","https://openalex.org/W4393407138","https://openalex.org/W4394998892","https://openalex.org/W4395106477","https://openalex.org/W6694517276","https://openalex.org/W6703652217","https://openalex.org/W6745499037","https://openalex.org/W6766978945","https://openalex.org/W6767997687","https://openalex.org/W6768723914","https://openalex.org/W6779863968","https://openalex.org/W6779999780","https://openalex.org/W6787953186","https://openalex.org/W6796581206","https://openalex.org/W6802310216","https://openalex.org/W6810802675","https://openalex.org/W6851775633","https://openalex.org/W6857732680"],"related_works":["https://openalex.org/W2496310356","https://openalex.org/W2780108937","https://openalex.org/W2048009773","https://openalex.org/W2121259868","https://openalex.org/W2140834465","https://openalex.org/W1842640819","https://openalex.org/W4376118324","https://openalex.org/W3133319229","https://openalex.org/W983888663","https://openalex.org/W2329486400"],"abstract_inverted_index":{"To":[0],"improve":[1,183],"data":[2],"processing":[3],"and":[4,15,45,110],"learning":[5,90],"capabilities,":[6],"DNN":[7,41,165],"models":[8,60],"are":[9,47],"developing":[10],"towards":[11],"increasingly":[12],"complex":[13],"structures":[14],"a":[16,35,96,138],"huge":[17],"number":[18],"of":[19,26,58,71,149],"parameters.":[20],"However,":[21],"the":[22,56,72,81,119,147,170],"limited":[23],"memory":[24,51,99,125],"capacity":[25],"specialized":[27],"acceleration":[28],"chips":[29],"such":[30],"as":[31],"GPUs":[32],"has":[33],"become":[34],"critical":[36],"constraint":[37],"in":[38,61],"exploring":[39],"advanced":[40],"models.":[42],"Memory":[43],"swapping":[44,109,151],"recomputation":[46,153],"two":[48],"effective":[49],"GPU":[50,98,124],"optimization":[52,100],"techniques":[53],"that":[54],"enable":[55],"training":[57,144,172,184],"larger":[59,130],"memory-constrained":[62],"hardware":[63],"environments.":[64],"Existing":[65],"methods":[66],"mostly":[67],"require":[68],"prior":[69],"knowledge":[70],"complete":[73],"computational":[74,83,104],"graph,":[75],"which":[76],"is":[77,126],"not":[78],"suitable":[79],"for":[80,102,163],"dynamic":[82,103],"graph":[84],"mode":[85],"adopted":[86],"by":[87,113,175,186],"mainstream":[88],"deep":[89],"frameworks.":[91],"This":[92],"paper":[93],"proposes":[94],"DOME,":[95],"tensor-level":[97],"method":[101],"graphs.":[105],"DOME":[106,136,167,181],"combines":[107],"tensor":[108,150],"recomputation,":[111],"inspired":[112],"cache":[114],"replacement":[115],"algorithms,":[116],"to":[117,177,188,191],"release":[118],"least":[120],"costly":[121],"tensors":[122],"when":[123],"insufficient,":[127],"thereby":[128],"supporting":[129],"batch":[131,173],"sizes":[132],"during":[133],"model":[134],"training.":[135],"employs":[137],"heuristic":[139],"evaluation":[140],"function":[141],"with":[142],"higher":[143],"efficiency,":[145],"estimating":[146],"cost":[148],"or":[152],"using":[154],"information":[155],"obtained":[156],"online":[157],"at":[158],"runtime.":[159],"Experiments":[160],"demonstrate":[161],"that,":[162],"different":[164],"models,":[166],"can":[168,182],"increase":[169],"maximum":[171],"size":[174],"1.56":[176],"2.33":[178],"times.":[179],"Additionally,":[180],"throughput":[185],"9.8%":[187],"35.0%":[189],"compared":[190],"SOTA":[192],"methods.":[193]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}