{"id":"https://openalex.org/W4389459222","doi":"https://doi.org/10.1109/tcsi.2023.3338471","title":"WinTA: An Efficient Reconfigurable CNN Training Accelerator With Decomposition Winograd","display_name":"WinTA: An Efficient Reconfigurable CNN Training Accelerator With Decomposition Winograd","publication_year":2023,"publication_date":"2023-12-07","ids":{"openalex":"https://openalex.org/W4389459222","doi":"https://doi.org/10.1109/tcsi.2023.3338471"},"language":"en","primary_location":{"id":"doi:10.1109/tcsi.2023.3338471","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsi.2023.3338471","pdf_url":null,"source":{"id":"https://openalex.org/S116977442","display_name":"IEEE Transactions on Circuits and Systems I Regular Papers","issn_l":"1549-8328","issn":["1549-8328","1558-0806"],"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 Circuits and Systems I: Regular Papers","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/A5059107361","display_name":"Jinming Lu","orcid":"https://orcid.org/0000-0002-7134-6514"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinming Lu","raw_affiliation_strings":["School of Electronic Science and Engineering, Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-7134-6514","affiliations":[{"raw_affiliation_string":"School of Electronic Science and Engineering, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015500761","display_name":"Hui Wang","orcid":"https://orcid.org/0009-0002-8690-3608"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Wang","raw_affiliation_strings":["School of Electronic Science and Engineering, Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0002-8690-3608","affiliations":[{"raw_affiliation_string":"School of Electronic Science and Engineering, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019940239","display_name":"Jun Lin","orcid":"https://orcid.org/0000-0003-2760-4333"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Lin","raw_affiliation_strings":["School of Electronic Science and Engineering, Nanjing University, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic Science and Engineering, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100696999","display_name":"Zhongfeng Wang","orcid":"https://orcid.org/0000-0002-7227-4786"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongfeng Wang","raw_affiliation_strings":["School of Electronic Science and Engineering, Naniing University, Naniing, China","School of Integrated Circuits, Sun Yat-sen University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-7227-4786","affiliations":[{"raw_affiliation_string":"School of Electronic Science and Engineering, Naniing University, Naniing, China","institution_ids":[]},{"raw_affiliation_string":"School of Integrated Circuits, Sun Yat-sen University, Shenzhen, China","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7859,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.74879152,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"71","issue":"2","first_page":"634","last_page":"645"},"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/T12676","display_name":"Machine Learning and ELM","score":0.9922000169754028,"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"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9912999868392944,"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":0.8696331977844238},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.743443489074707},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6471086144447327},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.5668160319328308},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.49217620491981506},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.4823819696903229},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.4716488718986511},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.44141173362731934},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.43921124935150146},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.38465389609336853},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.3800012469291687},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3436630368232727},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3007183074951172},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.17514988780021667}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8696331977844238},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.743443489074707},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6471086144447327},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.5668160319328308},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.49217620491981506},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.4823819696903229},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.4716488718986511},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.44141173362731934},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.43921124935150146},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.38465389609336853},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.3800012469291687},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3436630368232727},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3007183074951172},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.17514988780021667},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsi.2023.3338471","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsi.2023.3338471","pdf_url":null,"source":{"id":"https://openalex.org/S116977442","display_name":"IEEE Transactions on Circuits and Systems I Regular Papers","issn_l":"1549-8328","issn":["1549-8328","1558-0806"],"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 Circuits and Systems I: Regular Papers","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4699999988079071,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[{"id":"https://openalex.org/G2250357272","display_name":null,"funder_award_id":"62174084","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4187776313","display_name":null,"funder_award_id":"2022YFB4400604","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W2172654076","https://openalex.org/W2183341477","https://openalex.org/W2557355796","https://openalex.org/W2627042741","https://openalex.org/W2787094505","https://openalex.org/W2888885397","https://openalex.org/W2890068895","https://openalex.org/W2898985762","https://openalex.org/W2910507280","https://openalex.org/W2913221350","https://openalex.org/W2917518248","https://openalex.org/W2921918777","https://openalex.org/W2949469598","https://openalex.org/W2964525696","https://openalex.org/W2977634443","https://openalex.org/W2997109118","https://openalex.org/W3000160544","https://openalex.org/W3013525232","https://openalex.org/W3018618942","https://openalex.org/W3040850704","https://openalex.org/W3091592563","https://openalex.org/W3092345941","https://openalex.org/W3105802176","https://openalex.org/W3137841151","https://openalex.org/W3208821873","https://openalex.org/W4210823275","https://openalex.org/W4285117917","https://openalex.org/W4285247940","https://openalex.org/W4287118909","https://openalex.org/W4287828539","https://openalex.org/W6762580018","https://openalex.org/W6774302960","https://openalex.org/W6786965630","https://openalex.org/W6790409148","https://openalex.org/W6796815506"],"related_works":["https://openalex.org/W2111241003","https://openalex.org/W4200391368","https://openalex.org/W2355315220","https://openalex.org/W2210979487","https://openalex.org/W2074043759","https://openalex.org/W2316202402","https://openalex.org/W2373535795","https://openalex.org/W1967938402","https://openalex.org/W2386041993","https://openalex.org/W1608572506"],"abstract_inverted_index":{"Convolutional":[0],"neural":[1],"networks":[2],"(CNNs)":[3],"are":[4],"expected":[5],"to":[6,48,100,139,183],"bridge":[7],"the":[8,12,19,49,71,125],"domain":[9],"shift":[10],"between":[11],"training":[13,21,41,89,186],"data":[14,112],"and":[15,35,52,75,110,141,150,161,171,179],"real-world":[16],"tasks.":[17],"Moreover,":[18],"efficient":[20,109],"of":[22,32,73,96,147,177],"CNNs":[23],"on":[24,42,124],"resource-constrained":[25],"platforms":[26],"has":[27],"become":[28],"more":[29],"important":[30],"because":[31],"communication":[33],"latency":[34],"privacy":[36],"concerns.":[37],"However,":[38],"deploying":[39],"CNN":[40,88,136],"edge":[43],"devices":[44],"is":[45],"challenging":[46],"due":[47],"intensive":[50],"computation":[51],"diverse":[53],"computational":[54],"patterns.":[55],"In":[56],"this":[57],"work,":[58],"we":[59,84,106],"firstly":[60],"propose":[61],"a":[62,86,94,116],"hybrid":[63],"decomposition":[64],"Winograd":[65,103],"(HDW)":[66],"method":[67],"that":[68,132],"significantly":[69],"reduces":[70],"number":[72],"multiplications":[74],"flexibly":[76],"handles":[77],"various":[78,102],"convolution":[79],"operations":[80],"during":[81],"training.":[82,137],"Secondly,":[83],"design":[85,167],"reconfigurable":[87],"accelerator,":[90],"named":[91],"WinTA,":[92],"utilizing":[93],"set":[95],"unified":[97],"transformation":[98],"units":[99],"support":[101],"operations.":[104],"Thirdly,":[105],"implement":[107],"an":[108],"flexible":[111],"access":[113],"scheme":[114],"using":[115],"hierarchical":[117],"barrel":[118],"shifter":[119],"network":[120],"(HBSN).":[121],"Experimental":[122],"results":[123],"Xilinx":[126],"Alveo":[127],"U50":[128],"FPGA":[129],"Card":[130],"demonstrate":[131],"WinTA":[133,144],"effectively":[134],"accelerates":[135],"Compared":[138],"CPU":[140],"GPU":[142],"implementations,":[143],"achieves":[145],"speedups":[146],"7.1":[148],"texttimes":[149,160,170,173],"1.65":[151],"texttimes,":[152,163],"respectively,":[153],"while":[154],"improving":[155],"energy":[156],"efficiency":[157,181],"by":[158],"26.6":[159],"10.4":[162],"respectively.":[164],"Additionally,":[165],"our":[166],"provides":[168],"1.24":[169],"2.04":[172],"improvements":[174],"in":[175],"terms":[176],"throughput":[178],"resource":[180],"compared":[182],"prior-art":[184],"FPGA-based":[185],"accelerator.":[187]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}