{"id":"https://openalex.org/W2979816092","doi":"https://doi.org/10.1145/3357238","title":"Layup","display_name":"Layup","publication_year":2019,"publication_date":"2019-10-11","ids":{"openalex":"https://openalex.org/W2979816092","doi":"https://doi.org/10.1145/3357238","mag":"2979816092"},"language":"en","primary_location":{"id":"doi:10.1145/3357238","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3357238","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3357238","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3357238","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5073349777","display_name":"Wenbin Jiang","orcid":"https://orcid.org/0000-0002-2085-9870"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wenbin Jiang","raw_affiliation_strings":["Huazhong University of Science and Technology, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101875456","display_name":"Yang Ma","orcid":"https://orcid.org/0000-0003-3719-3195"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Ma","raw_affiliation_strings":["Huazhong University of Science and Technology, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114377956","display_name":"Bo Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Liu","raw_affiliation_strings":["Huazhong University of Science and Technology, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033955608","display_name":"Haikun Liu","orcid":"https://orcid.org/0000-0003-4290-1408"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haikun Liu","raw_affiliation_strings":["Huazhong University of Science and Technology, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030759821","display_name":"Bing Zhou","orcid":"https://orcid.org/0000-0002-0838-7858"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Bing Bing Zhou","raw_affiliation_strings":["The University of Sydney, NSW, Australia"],"affiliations":[{"raw_affiliation_string":"The University of Sydney, NSW, Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101670573","display_name":"Jian Zhu","orcid":"https://orcid.org/0000-0002-3835-4627"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Zhu","raw_affiliation_strings":["Huazhong University of Science and Technology, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003766128","display_name":"Song Wu","orcid":"https://orcid.org/0000-0001-8690-127X"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Song Wu","raw_affiliation_strings":["Huazhong University of Science and Technology, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022262922","display_name":"Hai Jin","orcid":"https://orcid.org/0000-0002-3934-7605"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hai Jin","raw_affiliation_strings":["Huazhong University of Science and Technology, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5073349777"],"corresponding_institution_ids":["https://openalex.org/I47720641"],"apc_list":null,"apc_paid":null,"fwci":0.608,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.72731479,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"16","issue":"4","first_page":"1","last_page":"23"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":1.0,"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":1.0,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9988999962806702,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.8808043003082275},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6061895489692688},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4484527111053467},{"id":"https://openalex.org/keywords/flat-memory-model","display_name":"Flat memory model","score":0.42908358573913574},{"id":"https://openalex.org/keywords/memory-management","display_name":"Memory management","score":0.4052393138408661},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3015245199203491},{"id":"https://openalex.org/keywords/semiconductor-memory","display_name":"Semiconductor memory","score":0.16216221451759338},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.10815536975860596}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8808043003082275},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6061895489692688},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4484527111053467},{"id":"https://openalex.org/C57863822","wikidata":"https://www.wikidata.org/wiki/Q905488","display_name":"Flat memory model","level":4,"score":0.42908358573913574},{"id":"https://openalex.org/C176649486","wikidata":"https://www.wikidata.org/wiki/Q2308807","display_name":"Memory management","level":3,"score":0.4052393138408661},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3015245199203491},{"id":"https://openalex.org/C98986596","wikidata":"https://www.wikidata.org/wiki/Q1143031","display_name":"Semiconductor memory","level":2,"score":0.16216221451759338},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.10815536975860596}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3357238","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3357238","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3357238","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3357238","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3357238","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3357238","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1288386159","display_name":null,"funder_award_id":"61672250, 61672251","funder_id":"https://openalex.org/F4320327720","funder_display_name":"Foundation for Innovative Research Groups of the National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320327720","display_name":"Foundation for Innovative Research Groups of the National Natural Science Foundation of China","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2979816092.pdf","grobid_xml":"https://content.openalex.org/works/W2979816092.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W164384110","https://openalex.org/W2056119007","https://openalex.org/W2094786337","https://openalex.org/W2097117768","https://openalex.org/W2108598243","https://openalex.org/W2112796928","https://openalex.org/W2152175008","https://openalex.org/W2155893237","https://openalex.org/W2183341477","https://openalex.org/W2194775991","https://openalex.org/W2513383847","https://openalex.org/W2549139847","https://openalex.org/W2558687840","https://openalex.org/W2604319603","https://openalex.org/W2621285511","https://openalex.org/W2790601347","https://openalex.org/W2808072032","https://openalex.org/W2891993230","https://openalex.org/W3103894541","https://openalex.org/W4247950230","https://openalex.org/W4301361180"],"related_works":["https://openalex.org/W2362277122","https://openalex.org/W2526783553","https://openalex.org/W2334181344","https://openalex.org/W2401095501","https://openalex.org/W2558276258","https://openalex.org/W261562921","https://openalex.org/W2138847","https://openalex.org/W1976766385","https://openalex.org/W2098974543","https://openalex.org/W4293054943"],"abstract_inverted_index":{"Although":[0],"GPUs":[1],"have":[2,19,38],"emerged":[3],"as":[4,141],"the":[5,8,43,51,62,102,155,181],"mainstream":[6],"for":[7,35,95,117],"acceleration":[9],"of":[10,46,54,64,120,157,184],"convolutional":[11,142],"neural":[12],"network":[13,159],"(CNN)":[14],"training":[15],"processes,":[16],"they":[17],"usually":[18],"limited":[20],"physical":[21],"memory,":[22,179],"meaning":[23],"that":[24,80,105,150],"it":[25],"is":[26,98,128,134],"hard":[27],"to":[28,41,49,136],"train":[29,172],"large-scale":[30],"CNN":[31],"models.":[32],"Many":[33],"methods":[34],"memory":[36,44,75,84,96,108,125],"optimization":[37,59,76,97,109],"been":[39],"proposed":[40],"decrease":[42],"consumption":[45],"CNNs":[47],"and":[48,86,144],"mitigate":[50],"increasing":[52],"scale":[53,156],"these":[55],"networks;":[56],"however,":[57],"this":[58],"comes":[60],"at":[61],"cost":[63],"an":[65],"obvious":[66],"drop":[67],"in":[68,114,130],"time":[69,88,115],"performance.":[70,89],"We":[71],"propose":[72],"a":[73,91,106,123,162],"new":[74,103,124],"strategy":[77],"named":[78],"Layup":[79,151],"realizes":[81],"both":[82],"better":[83,87],"efficiency":[85],"First,":[90],"fast":[92],"layer-type-specific":[93],"method":[94,127],"presented,":[99],"based":[100],"on":[101,161],"finding":[104],"single":[107,163],"often":[110],"shows":[111],"dramatic":[112],"differences":[113],"performance":[116,167],"different":[118],"types":[119],"layers.":[121],"Second,":[122],"reuse":[126],"presented":[129],"which":[131],"greater":[132],"attention":[133],"paid":[135],"multi-type":[137],"intermediate":[138],"data":[139],"such":[140],"workspaces":[143],"cuDNN":[145],"handle":[146],"data.":[147],"Experiments":[148],"show":[149],"can":[152,171],"significantly":[153],"increase":[154],"extra-deep":[158],"models":[160],"GPU":[164],"with":[165,174,186],"lower":[166],"loss.":[168],"It":[169],"even":[170],"ResNet":[173],"2,504":[175],"layers":[176,188],"using":[177],"12GB":[178],"outperforming":[180],"state-of-the-art":[182],"work":[183],"SuperNeurons":[185],"1,920":[187],"(batch":[189],"size":[190],"=":[191],"16).":[192]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3}],"updated_date":"2026-03-01T08:55:55.761014","created_date":"2019-10-18T00:00:00"}