{"id":"https://openalex.org/W4285148475","doi":"https://doi.org/10.1109/tc.2022.3180991","title":"HOME: A Holistic GPU Memory Management Framework for Deep Learning","display_name":"HOME: A Holistic GPU Memory Management Framework for Deep Learning","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4285148475","doi":"https://doi.org/10.1109/tc.2022.3180991"},"language":"en","primary_location":{"id":"doi:10.1109/tc.2022.3180991","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tc.2022.3180991","pdf_url":null,"source":{"id":"https://openalex.org/S157670870","display_name":"IEEE Transactions on Computers","issn_l":"0018-9340","issn":["0018-9340","1557-9956","2326-3814"],"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 Computers","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/A5004997843","display_name":"Shuibing He","orcid":"https://orcid.org/0000-0002-7075-4153"},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shuibing He","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I168879160"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101585958","display_name":"Ping Chen","orcid":"https://orcid.org/0000-0001-6973-0755"},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ping Chen","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I168879160"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071132411","display_name":"Shuaiben Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuaiben Chen","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I168879160"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100414958","display_name":"Zheng Li","orcid":"https://orcid.org/0000-0001-8536-1646"},"institutions":[{"id":"https://openalex.org/I24010308","display_name":"Stockton University","ror":"https://ror.org/0442n1j98","country_code":"US","type":"education","lineage":["https://openalex.org/I24010308"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zheng Li","raw_affiliation_strings":["Computer Science Program, School of Business, Stockton University, USA"],"affiliations":[{"raw_affiliation_string":"Computer Science Program, School of Business, Stockton University, USA","institution_ids":["https://openalex.org/I24010308"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043851369","display_name":"Siling Yang","orcid":"https://orcid.org/0000-0002-2208-559X"},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siling Yang","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I168879160"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100681962","display_name":"Weijian Chen","orcid":"https://orcid.org/0000-0001-8296-2673"},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weijian Chen","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I168879160"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103017455","display_name":"Lidan Shou","orcid":"https://orcid.org/0000-0001-8062-8356"},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lidan Shou","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I168879160"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5004997843"],"corresponding_institution_ids":["https://openalex.org/I168879160"],"apc_list":null,"apc_paid":null,"fwci":2.4976,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.88963335,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"13"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9990000128746033,"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":0.9990000128746033,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9987999796867371,"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/T12303","display_name":"Tensor decomposition and applications","score":0.993399977684021,"subfield":{"id":"https://openalex.org/subfields/2605","display_name":"Computational Mathematics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8086743950843811},{"id":"https://openalex.org/keywords/memory-footprint","display_name":"Memory footprint","score":0.7305572628974915},{"id":"https://openalex.org/keywords/tensor","display_name":"Tensor (intrinsic definition)","score":0.5720953345298767},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5051258206367493},{"id":"https://openalex.org/keywords/particle-swarm-optimization","display_name":"Particle swarm optimization","score":0.49337878823280334},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.4384418725967407},{"id":"https://openalex.org/keywords/memory-management","display_name":"Memory management","score":0.4364834129810333},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4245802164077759},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.4184044897556305},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.4111034870147705},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3893055021762848},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.3766900897026062},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.29134148359298706},{"id":"https://openalex.org/keywords/overlay","display_name":"Overlay","score":0.12771835923194885},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.08683198690414429}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8086743950843811},{"id":"https://openalex.org/C74912251","wikidata":"https://www.wikidata.org/wiki/Q6815727","display_name":"Memory footprint","level":2,"score":0.7305572628974915},{"id":"https://openalex.org/C155281189","wikidata":"https://www.wikidata.org/wiki/Q3518150","display_name":"Tensor (intrinsic definition)","level":2,"score":0.5720953345298767},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5051258206367493},{"id":"https://openalex.org/C85617194","wikidata":"https://www.wikidata.org/wiki/Q2072794","display_name":"Particle swarm optimization","level":2,"score":0.49337878823280334},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.4384418725967407},{"id":"https://openalex.org/C176649486","wikidata":"https://www.wikidata.org/wiki/Q2308807","display_name":"Memory management","level":3,"score":0.4364834129810333},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4245802164077759},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.4184044897556305},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.4111034870147705},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3893055021762848},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3766900897026062},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.29134148359298706},{"id":"https://openalex.org/C136085584","wikidata":"https://www.wikidata.org/wiki/Q910289","display_name":"Overlay","level":2,"score":0.12771835923194885},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.08683198690414429},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tc.2022.3180991","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tc.2022.3180991","pdf_url":null,"source":{"id":"https://openalex.org/S157670870","display_name":"IEEE Transactions on Computers","issn_l":"0018-9340","issn":["0018-9340","1557-9956","2326-3814"],"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 Computers","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":53,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W1919191429","https://openalex.org/W2152195021","https://openalex.org/W2155893237","https://openalex.org/W2194775991","https://openalex.org/W2279098554","https://openalex.org/W2338908902","https://openalex.org/W2402144811","https://openalex.org/W2489529491","https://openalex.org/W2512971201","https://openalex.org/W2613099550","https://openalex.org/W2791673912","https://openalex.org/W2798707674","https://openalex.org/W2883283076","https://openalex.org/W2883830791","https://openalex.org/W2886851211","https://openalex.org/W2896457183","https://openalex.org/W2911892981","https://openalex.org/W2944850467","https://openalex.org/W2963854351","https://openalex.org/W2963959650","https://openalex.org/W2971843695","https://openalex.org/W2979816092","https://openalex.org/W3010830594","https://openalex.org/W3012479151","https://openalex.org/W3012514909","https://openalex.org/W3016842236","https://openalex.org/W3035078899","https://openalex.org/W3037639655","https://openalex.org/W3038086838","https://openalex.org/W3089650620","https://openalex.org/W3101104221","https://openalex.org/W3101543398","https://openalex.org/W3103572230","https://openalex.org/W3167436278","https://openalex.org/W3206867815","https://openalex.org/W4294371482","https://openalex.org/W4295312788","https://openalex.org/W4297775537","https://openalex.org/W4301361180","https://openalex.org/W6637373629","https://openalex.org/W6638839971","https://openalex.org/W6677580257","https://openalex.org/W6695314431","https://openalex.org/W6703652217","https://openalex.org/W6737664043","https://openalex.org/W6741502269","https://openalex.org/W6747917562","https://openalex.org/W6755207826","https://openalex.org/W6766978945","https://openalex.org/W6768723914","https://openalex.org/W6799023841","https://openalex.org/W6898611122"],"related_works":["https://openalex.org/W1976766385","https://openalex.org/W2125264433","https://openalex.org/W4237401226","https://openalex.org/W4236777984","https://openalex.org/W2112457107","https://openalex.org/W2159716314","https://openalex.org/W2244179743","https://openalex.org/W2293728877","https://openalex.org/W2106097839","https://openalex.org/W4200309432"],"abstract_inverted_index":{"We":[0,109],"propose":[1],"HOlistic":[2],"MEmory":[3],"management":[4],"(HOME),":[5],"a":[6,64,84],"new":[7],"framework":[8],"for":[9,76],"performing":[10],"tensor":[11,26,29,57,78],"placements":[12],"in":[13,56,112,139],"large":[14],"DNN":[15,44,51,81,121],"training":[16],"when":[17],"GPU":[18,33,106],"memory":[19,34,107],"space":[20],"is":[21],"not":[22],"enough.":[23],"HOME":[24,47,62,98,111,127,142],"combines":[25],"swapping":[27],"with":[28,83],"recomputation":[30],"to":[31,70,99,135,151,159],"reduce":[32],"footprint.":[35],"Different":[36],"from":[37],"existing":[38],"work":[39],"that":[40,126],"only":[41],"considers":[42],"partial":[43],"model":[45,52,82,95],"information,":[46],"takes":[48],"the":[49,72,80,93,104,145,154],"holistic":[50,90],"information":[53,96],"into":[54],"account":[55],"placement":[58,75],"decisions.":[59],"More":[60],"specifically,":[61],"uses":[63],"custom-designed":[65],"particle":[66],"swarm":[67],"optimization":[68],"algorithm":[69],"achieve":[71],"globally":[73],"optimized":[74],"each":[77],"of":[79,92],"greatly":[85],"reduced":[86],"searching":[87],"space.":[88],"This":[89],"awareness":[91],"whole":[94],"enables":[97],"obtain":[100],"high":[101],"performance":[102],"under":[103],"given":[105],"constraint.":[108],"implement":[110],"PyTorch":[113,156],"and":[114,131,137,157],"conduct":[115],"our":[116],"experiments":[117],"using":[118],"six":[119],"popular":[120],"models.":[122],"Experimental":[123],"results":[124],"show":[125],"can":[128,143],"outperform":[129],"vDNN":[130],"Capuchin":[132],"by":[133,149],"up":[134,150,158],"5.7×":[136],"1.3×":[138,160],"throughput.":[140],"Furthermore,":[141],"improve":[144],"maximum":[146],"batch":[147],"size":[148],"2.8×":[152],"than":[153,161],"original":[155],"Capuchin.":[162]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}