{"id":"https://openalex.org/W3090600872","doi":"https://doi.org/10.1109/tcad.2020.3012323","title":"WinoNN: Optimizing FPGA-Based Convolutional Neural Network Accelerators Using Sparse Winograd Algorithm","display_name":"WinoNN: Optimizing FPGA-Based Convolutional Neural Network Accelerators Using Sparse Winograd Algorithm","publication_year":2020,"publication_date":"2020-10-02","ids":{"openalex":"https://openalex.org/W3090600872","doi":"https://doi.org/10.1109/tcad.2020.3012323","mag":"3090600872"},"language":"en","primary_location":{"id":"doi:10.1109/tcad.2020.3012323","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcad.2020.3012323","pdf_url":null,"source":{"id":"https://openalex.org/S100835903","display_name":"IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems","issn_l":"0278-0070","issn":["0278-0070","1937-4151"],"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 Computer-Aided Design of Integrated Circuits and Systems","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/A5100329044","display_name":"Xuan Wang","orcid":"https://orcid.org/0000-0003-3065-4606"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuan Wang","raw_affiliation_strings":["School of Computer Science and Technology, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0003-3065-4606","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011884768","display_name":"Chao Wang","orcid":"https://orcid.org/0000-0002-9403-5575"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Wang","raw_affiliation_strings":["School of Computer Science and Technology, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-9403-5575","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039214577","display_name":"Jing Cao","orcid":"https://orcid.org/0000-0002-9485-4204"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Cao","raw_affiliation_strings":["School of Computer Science and Technology, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-9485-4204","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072915437","display_name":"Lei Gong","orcid":"https://orcid.org/0000-0002-8391-5526"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Gong","raw_affiliation_strings":["School of Computer Science and Technology, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-8391-5526","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077322091","display_name":"Xuehai Zhou","orcid":"https://orcid.org/0000-0002-8360-3143"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuehai Zhou","raw_affiliation_strings":["School of Computer Science and Technology, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-8360-3143","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":2.875,"has_fulltext":false,"cited_by_count":48,"citation_normalized_percentile":{"value":0.92550124,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"39","issue":"11","first_page":"4290","last_page":"4302"},"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/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.9991000294685364,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9954000115394592,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8063000440597534},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.7127408981323242},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6491442918777466},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.6448058485984802},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6321098208427429},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.4659838080406189},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.4648401141166687},{"id":"https://openalex.org/keywords/design-space-exploration","display_name":"Design space exploration","score":0.4280874729156494},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.42788201570510864},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.4171203076839447},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3968116343021393},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.3186611533164978},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.29984790086746216},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2716411352157593}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8063000440597534},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.7127408981323242},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6491442918777466},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.6448058485984802},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6321098208427429},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.4659838080406189},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.4648401141166687},{"id":"https://openalex.org/C2776221188","wikidata":"https://www.wikidata.org/wiki/Q21072556","display_name":"Design space exploration","level":2,"score":0.4280874729156494},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.42788201570510864},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.4171203076839447},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3968116343021393},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.3186611533164978},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.29984790086746216},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2716411352157593},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcad.2020.3012323","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcad.2020.3012323","pdf_url":null,"source":{"id":"https://openalex.org/S100835903","display_name":"IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems","issn_l":"0278-0070","issn":["0278-0070","1937-4151"],"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 Computer-Aided Design of Integrated Circuits and Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8999999761581421,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[{"id":"https://openalex.org/G3656052465","display_name":null,"funder_award_id":"2017497","funder_id":"https://openalex.org/F4320321133","funder_display_name":"Chinese Academy of Sciences"},{"id":"https://openalex.org/G7639841928","display_name":null,"funder_award_id":"BK20181193","funder_id":"https://openalex.org/F4320322769","funder_display_name":"Natural Science Foundation of Jiangsu Province"},{"id":"https://openalex.org/G8758304440","display_name":null,"funder_award_id":"61976200","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation 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/F4320321133","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35"},{"id":"https://openalex.org/F4320322769","display_name":"Natural Science Foundation of Jiangsu Province","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W2000967104","https://openalex.org/W2048266589","https://openalex.org/W2097117768","https://openalex.org/W2119144962","https://openalex.org/W2152839228","https://openalex.org/W2172654076","https://openalex.org/W2194775991","https://openalex.org/W2406293284","https://openalex.org/W2442974303","https://openalex.org/W2565851976","https://openalex.org/W2592875630","https://openalex.org/W2625457103","https://openalex.org/W2627042741","https://openalex.org/W2729080111","https://openalex.org/W2789246071","https://openalex.org/W2806397907","https://openalex.org/W2809121165","https://openalex.org/W2883927138","https://openalex.org/W2895394565","https://openalex.org/W2899431594","https://openalex.org/W2900158633","https://openalex.org/W2904902077","https://openalex.org/W2940399336","https://openalex.org/W2962835968","https://openalex.org/W2962883557","https://openalex.org/W2963037989","https://openalex.org/W2963122961","https://openalex.org/W2963416938","https://openalex.org/W2963674932","https://openalex.org/W2977634443","https://openalex.org/W3003431487","https://openalex.org/W3023485717","https://openalex.org/W3106250896","https://openalex.org/W4240168186","https://openalex.org/W4243682116","https://openalex.org/W6637373629","https://openalex.org/W6713184358","https://openalex.org/W6742162214","https://openalex.org/W6747766405","https://openalex.org/W6785652829"],"related_works":["https://openalex.org/W2168940796","https://openalex.org/W4282568311","https://openalex.org/W2951473296","https://openalex.org/W2883928845","https://openalex.org/W4288420200","https://openalex.org/W3145095675","https://openalex.org/W2024329643","https://openalex.org/W4365793791","https://openalex.org/W3134072570","https://openalex.org/W2171195786"],"abstract_inverted_index":{"In":[0,115],"recent":[1],"years,":[2],"a":[3,49,120,169,178,195,214],"variety":[4],"of":[5,43,69,86,164],"accelerators":[6,51,227],"on":[7,52,72,213,228,243],"FPGAs":[8,53],"have":[9,36,104],"been":[10],"proposed":[11,168],"to":[12,65,182,187,201,208,223],"speed":[13],"up":[14],"the":[15,39,57,67,73,99,107,112,128,142,162,189,203,210,249,263],"convolutional":[16],"neural":[17],"network":[18,34,63],"(CNN)":[19],"in":[20,84,173,237],"many":[21],"domain-specific":[22],"application":[23],"fields.":[24],"Besides,":[25],"some":[26,88],"optimization":[27],"algorithms,":[28],"such":[29],"as":[30],"fast":[31,58],"algorithms":[32],"and":[33,62,136,198,257],"sparsity,":[35,135,149],"greatly":[37],"reduced":[38],"theoretical":[40,196],"computational":[41],"workload":[42],"CNN":[44],"inference.":[45],"There":[46],"are":[47],"currently":[48],"few":[50],"that":[54,246],"support":[55],"both":[56],"Winograd":[59,226],"algorithm":[60],"(WinoA)":[61],"sparsity":[64,138],"minimize":[66,141,188],"amount":[68],"computation.":[70],"However,":[71],"one":[74],"hand,":[75,101],"these":[76,102],"architectures":[77],"feed":[78],"data":[79,185],"into":[80],"processing":[81,253],"elements":[82],"(PEs)":[83],"units":[85],"blocks,":[87],"boundary":[89,190],"losses":[90],"caused":[91,146],"by":[92,131,147],"sparse":[93,113,165,225,265],"irregularities":[94,163],"cannot":[95],"be":[96],"avoided.":[97],"On":[98],"other":[100],"works":[103],"not":[105,235],"discussed":[106],"design":[108,204,220],"space":[109],"exploration":[110],"under":[111],"condition.":[114],"this":[116],"article,":[117],"we":[118,167,193,247],"propose":[119],"novel":[121,170],"accelerator":[122],"called":[123,154],"WINONN.":[124],"We":[125],"fully":[126],"discuss":[127],"challenges":[129],"faced":[130],"supporting":[132],"WinoA,":[133],"weight":[134],"activation":[137,148],"simultaneously.":[139],"To":[140,160],"online":[143],"encoding":[144,152],"overhead":[145],"an":[150],"efficient":[151],"format":[153],"multibit":[155],"mask":[156],"(MBM)":[157],"is":[158,234],"proposed.":[159],"handle":[161],"data,":[166],"Scatter-Compute-Gather":[171],"method":[172,200],"hardware":[174],"design,":[175],"combined":[176],"with":[177,262],"freely":[179],"sliding":[180],"buffer":[181],"achieve":[183,248],"fine-grained":[184],"loading":[186],"waste.":[191],"Finally,":[192],"combine":[194],"analysis":[197],"experimental":[199,241],"explore":[202],"space,":[205],"allowing":[206],"WINONN":[207],"get":[209],"best":[211],"performance":[212],"specific":[215],"FPGA.":[216],"Our":[217],"high":[218],"scalability":[219],"enables":[221],"us":[222],"deploy":[224],"very":[229],"small":[230],"embedded":[231],"FPGAs,":[232],"which":[233],"supported":[236],"previous":[238],"works.":[239],"The":[240],"results":[242],"VGG16":[244],"show":[245],"highest":[250,258],"digital":[251],"signal":[252],"unit":[254],"(DSP)":[255],"efficiency":[256,260],"energy":[259],"compared":[261],"state-of-the-art":[264],"architectures.":[266]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":13},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}