{"id":"https://openalex.org/W4386474839","doi":"https://doi.org/10.1109/isvlsi59464.2023.10238574","title":"An FPGA-Based Reconfigurable CNN Training Accelerator Using Decomposable Winograd","display_name":"An FPGA-Based Reconfigurable CNN Training Accelerator Using Decomposable Winograd","publication_year":2023,"publication_date":"2023-06-20","ids":{"openalex":"https://openalex.org/W4386474839","doi":"https://doi.org/10.1109/isvlsi59464.2023.10238574"},"language":"en","primary_location":{"id":"doi:10.1109/isvlsi59464.2023.10238574","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isvlsi59464.2023.10238574","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Computer Society Annual Symposium on VLSI (ISVLSI)","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/A5107844129","display_name":"Hui Wang","orcid":"https://orcid.org/0000-0001-6491-9612"},"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":true,"raw_author_name":"Hui Wang","raw_affiliation_strings":["Nanjing University,School of Electronic Science and Engineering,Nanjing,China","School of Electronic Science and Engineering, Nanjing University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University,School of Electronic Science and Engineering,Nanjing,China","institution_ids":["https://openalex.org/I881766915"]},{"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/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":["Nanjing University,School of Electronic Science and Engineering,Nanjing,China","School of Electronic Science and Engineering, Nanjing University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University,School of Electronic Science and Engineering,Nanjing,China","institution_ids":["https://openalex.org/I881766915"]},{"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":["Nanjing University,School of Electronic Science and Engineering,Nanjing,China","School of Electronic Science and Engineering, Nanjing University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University,School of Electronic Science and Engineering,Nanjing,China","institution_ids":["https://openalex.org/I881766915"]},{"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/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":"Zhongfeng Wang","raw_affiliation_strings":["Nanjing University,School of Electronic Science and Engineering,Nanjing,China","School of Electronic Science and Engineering, Nanjing University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University,School of Electronic Science and Engineering,Nanjing,China","institution_ids":["https://openalex.org/I881766915"]},{"raw_affiliation_string":"School of Electronic Science and Engineering, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5107844129"],"corresponding_institution_ids":["https://openalex.org/I881766915"],"apc_list":null,"apc_paid":null,"fwci":0.6141,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.69629011,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998000264167786,"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":0.9998000264167786,"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/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9983999729156494,"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":0.8211543560028076},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.7821042537689209},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6672643423080444},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.6542623043060303},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4911348521709442},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.48783329129219055},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.4727157950401306},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.4606720209121704},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.45924049615859985},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.3908502161502838},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.331093966960907},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3075501322746277},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.28107309341430664},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.25868865847587585},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.11427250504493713},{"id":"https://openalex.org/keywords/wireless","display_name":"Wireless","score":0.09975254535675049}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8211543560028076},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.7821042537689209},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6672643423080444},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.6542623043060303},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4911348521709442},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.48783329129219055},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.4727157950401306},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.4606720209121704},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.45924049615859985},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.3908502161502838},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.331093966960907},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3075501322746277},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28107309341430664},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.25868865847587585},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.11427250504493713},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.09975254535675049},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/isvlsi59464.2023.10238574","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isvlsi59464.2023.10238574","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Computer Society Annual Symposium on VLSI (ISVLSI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6800000071525574,"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1487564550","https://openalex.org/W1745334888","https://openalex.org/W2144172034","https://openalex.org/W2172654076","https://openalex.org/W2745150820","https://openalex.org/W2768993447","https://openalex.org/W2913221350","https://openalex.org/W2949469598","https://openalex.org/W2977634443","https://openalex.org/W2997109118","https://openalex.org/W3000160544","https://openalex.org/W3018618942","https://openalex.org/W3099036286","https://openalex.org/W3126707779","https://openalex.org/W4210823275","https://openalex.org/W4287118909","https://openalex.org/W4287828539","https://openalex.org/W6681239517","https://openalex.org/W6774302960","https://openalex.org/W6796815506"],"related_works":["https://openalex.org/W2111241003","https://openalex.org/W2355315220","https://openalex.org/W4200391368","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":[2,129],"(CNNs)":[3],"have":[4],"been":[5],"widely":[6],"used":[7],"in":[8,11,21,168,177],"computer":[9],"vision":[10],"recent":[12],"years.":[13],"However,":[14],"the":[15,32,46,50,65,68,74,181],"huge":[16],"amount":[17],"of":[18,48,67,70,76,91,113,170],"computation":[19],"involved":[20],"CNN":[22,40],"training":[23,41,88,102],"limits":[24],"its":[25],"application":[26,69],"on":[27,78,141,160],"embedded":[28],"devices.":[29],"To":[30],"solve":[31],"dilemma,":[33],"this":[34],"paper":[35],"proposes":[36],"an":[37],"FPGA-based":[38],"reconfigurable":[39,87],"accelerator.":[42],"First,":[43],"we":[44,84],"explore":[45],"possibility":[47],"using":[49],"Winograd":[51,59,71,77,94,123],"algorithm":[52],"to":[53,120,150,153,165],"accelerate":[54],"convolutions.":[55],"An":[56],"input-aligned":[57],"decomposable":[58],"method":[60,146],"is":[61],"proposed":[62],"that":[63,98],"broadens":[64],"scope":[66],"and":[72,133,143,172],"simplifies":[73],"implementation":[75],"a":[79,86,92,174],"unified":[80,114],"processing":[81,95],"element.":[82],"Second,":[83],"propose":[85],"architecture":[89],"consisting":[90],"transposable":[93],"element":[96],"array":[97],"can":[99],"perform":[100],"different":[101],"phases":[103],"with":[104],"high":[105],"parallelism":[106],"under":[107],"limited":[108],"resource":[109,178],"costs.":[110],"A":[111],"series":[112],"data":[115,135],"transformation":[116],"units":[117],"are":[118],"designed":[119],"support":[121],"various":[122],"operations.":[124],"The":[125],"hierarchical":[126],"barrel":[127],"shift":[128],"work":[130],"for":[131],"flexible":[132],"complex":[134],"access":[136],"without":[137],"bank":[138],"conflict.":[139],"Evaluated":[140],"VGG16":[142],"ResNet18,":[144],"our":[145,157],"reduces":[147],"multiplications":[148],"up":[149,164],"$2.4\\times$":[151],"compared":[152],"conventional":[154],"convolution.":[155],"Additionally,":[156],"accelerator":[158],"implemented":[159],"Alveo":[161],"U200":[162],"achieves":[163],"918.57":[166],"GOPS":[167],"terms":[169],"throughput":[171],"shows":[173],"$3.18\\times$":[175],"improvement":[176],"efficiency":[179],"over":[180],"prior":[182],"art.":[183]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}