{"id":"https://openalex.org/W2784248212","doi":"https://doi.org/10.1109/bigdata.2017.8257926","title":"ooc_cuDNN: Accommodating convolutional neural networks over GPU memory capacity","display_name":"ooc_cuDNN: Accommodating convolutional neural networks over GPU memory capacity","publication_year":2017,"publication_date":"2017-12-01","ids":{"openalex":"https://openalex.org/W2784248212","doi":"https://doi.org/10.1109/bigdata.2017.8257926","mag":"2784248212"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata.2017.8257926","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2017.8257926","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Big Data (Big Data)","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/A5036439738","display_name":"Yuki Ito","orcid":"https://orcid.org/0000-0003-1617-1595"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Yuki Ito","raw_affiliation_strings":["Tokyo Institute of Technology, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology, Tokyo, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041942185","display_name":"Ryo Matsumiya","orcid":null},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryo Matsumiya","raw_affiliation_strings":["Tokyo Institute of Technology, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology, Tokyo, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011254074","display_name":"Toshio Endo","orcid":"https://orcid.org/0000-0001-7297-6211"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Toshio Endo","raw_affiliation_strings":["Tokyo Institute of Technology, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology, Tokyo, Japan","institution_ids":["https://openalex.org/I114531698"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5036439738"],"corresponding_institution_ids":["https://openalex.org/I114531698"],"apc_list":null,"apc_paid":null,"fwci":0.7282,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.81332121,"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":"183","last_page":"192"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998999834060669,"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":0.9998999834060669,"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/T11105","display_name":"Advanced Image Processing Techniques","score":0.9977999925613403,"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/T11019","display_name":"Image Enhancement Techniques","score":0.9976000189781189,"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":0.853645384311676},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7466751337051392},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.7335222959518433},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5565812587738037},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5203289985656738},{"id":"https://openalex.org/keywords/memory-management","display_name":"Memory management","score":0.4749757647514343},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.464969664812088},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.4542752206325531},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.42611074447631836},{"id":"https://openalex.org/keywords/performance-improvement","display_name":"Performance improvement","score":0.42377355694770813},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.387823224067688},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.20054471492767334},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.10866641998291016},{"id":"https://openalex.org/keywords/semiconductor-memory","display_name":"Semiconductor memory","score":0.10086849331855774}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.853645384311676},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7466751337051392},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.7335222959518433},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5565812587738037},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5203289985656738},{"id":"https://openalex.org/C176649486","wikidata":"https://www.wikidata.org/wiki/Q2308807","display_name":"Memory management","level":3,"score":0.4749757647514343},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.464969664812088},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.4542752206325531},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.42611074447631836},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.42377355694770813},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.387823224067688},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.20054471492767334},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.10866641998291016},{"id":"https://openalex.org/C98986596","wikidata":"https://www.wikidata.org/wiki/Q1143031","display_name":"Semiconductor memory","level":2,"score":0.10086849331855774},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata.2017.8257926","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2017.8257926","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5600000023841858,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1667652561","https://openalex.org/W1686810756","https://openalex.org/W1885185971","https://openalex.org/W2102017903","https://openalex.org/W2155893237","https://openalex.org/W2163605009","https://openalex.org/W2339765813","https://openalex.org/W2394932179","https://openalex.org/W2402144811","https://openalex.org/W2489529491","https://openalex.org/W2561801540","https://openalex.org/W2953384591","https://openalex.org/W2962835968","https://openalex.org/W2963684088","https://openalex.org/W2964174152","https://openalex.org/W4256309825","https://openalex.org/W4302296459","https://openalex.org/W6637373629","https://openalex.org/W6684191040","https://openalex.org/W6685352114","https://openalex.org/W6711962127","https://openalex.org/W6713134421"],"related_works":["https://openalex.org/W4312417841","https://openalex.org/W4321369474","https://openalex.org/W2731899572","https://openalex.org/W3133861977","https://openalex.org/W4200173597","https://openalex.org/W3116150086","https://openalex.org/W2011159963","https://openalex.org/W1981557297","https://openalex.org/W2791204867","https://openalex.org/W1997955449"],"abstract_inverted_index":{"GPUs":[0],"are":[1,99],"widely":[2],"used":[3],"to":[4,23,48,105],"accelerate":[5],"deep":[6,73],"learning":[7,74],"with":[8,127,132],"convolutional":[9],"neural":[10],"networks":[11],"(CNNs).":[12],"However,":[13],"since":[14],"GPU":[15,52,126],"memory":[16,53,122],"capacity":[17,54,56],"is":[18,21,62,68],"limited,":[19],"it":[20],"difficult":[22],"implement":[24],"efficient":[25],"programs":[26],"that":[27],"compute":[28,49],"large":[29],"CNNs":[30,50],"on":[31,84,123],"GPU.":[32],"This":[33],"paper":[34],"describes":[35],"the":[36],"design":[37],"and":[38,71],"implementation":[39],"of":[40,57,65,101],"out-of-core":[41],"cuDNN":[42,61,79,94],"(ooc":[43],"cuDNN)":[44],"library.":[45],"It":[46],"supports":[47],"exceeding":[51],"using":[55,136],"CPU":[58],"memory.":[59,130],"ooc":[60,78,93,111],"an":[63,133],"extension":[64],"cuDNN,":[66,112,137],"which":[67,98],"high":[69],"performance":[70,86,89,138],"popular":[72],"library":[75],"for":[76,88],"GPUs.":[77],"divides":[80],"CNN":[81,116],"computation":[82],"based":[83],"its":[85],"model":[87],"improvement.":[90],"In":[91],"addition,":[92],"provides":[95],"fused":[96],"functions,":[97],"combinations":[100],"several":[102],"kernel":[103],"functions":[104],"reduce":[106],"extra":[107],"communication":[108],"costs.":[109],"With":[110],"we":[113],"successfully":[114],"computed":[115],"requiring":[117],"more":[118],"than":[119],"60":[120],"GB":[121,129],"a":[124],"single":[125],"16":[128],"Compared":[131],"in-core":[134],"case":[135],"degradation":[139],"was":[140],"13%.":[141]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}