{"id":"https://openalex.org/W7131381843","doi":"https://doi.org/10.1109/tvlsi.2026.3661565","title":"RV-WINO: A RISC-V Neural Network Accelerator Based on Winograd Algorithm Fabricated in 55-nm CMOS Process","display_name":"RV-WINO: A RISC-V Neural Network Accelerator Based on Winograd Algorithm Fabricated in 55-nm CMOS Process","publication_year":2026,"publication_date":"2026-02-25","ids":{"openalex":"https://openalex.org/W7131381843","doi":"https://doi.org/10.1109/tvlsi.2026.3661565"},"language":null,"primary_location":{"id":"doi:10.1109/tvlsi.2026.3661565","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tvlsi.2026.3661565","pdf_url":null,"source":{"id":"https://openalex.org/S37538908","display_name":"IEEE Transactions on Very Large Scale Integration (VLSI) Systems","issn_l":"1063-8210","issn":["1063-8210","1557-9999"],"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 Very Large Scale Integration (VLSI) 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":null,"display_name":"Xingbo Wang","orcid":"https://orcid.org/0000-0001-9349-2718"},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingbo Wang","raw_affiliation_strings":["Department of Electronic and Electrical Engineering, Southern University of Science and Technology, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0001-9349-2718","affiliations":[{"raw_affiliation_string":"Department of Electronic and Electrical Engineering, Southern University of Science and Technology, Shenzhen, China","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103194141","display_name":"Yucong Huang","orcid":"https://orcid.org/0000-0002-8499-4254"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yucong Huang","raw_affiliation_strings":["Department of Electronic and Electrical Engineering, The Hong Kong University of Science and Technology, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0002-8499-4254","affiliations":[{"raw_affiliation_string":"Department of Electronic and Electrical Engineering, The Hong Kong University of Science and Technology, Hong Kong, China","institution_ids":["https://openalex.org/I200769079","https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101304047","display_name":"Qu Lu","orcid":"https://orcid.org/0009-0004-0524-6277"},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qu Lu","raw_affiliation_strings":["Department of Electronic and Electrical Engineering, Southern University of Science and Technology, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic and Electrical Engineering, Southern University of Science and Technology, Shenzhen, China","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126789416","display_name":"Xinyu Kang","orcid":null},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinyu Kang","raw_affiliation_strings":["Department of Electronic and Electrical Engineering, Southern University of Science and Technology, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic and Electrical Engineering, Southern University of Science and Technology, Shenzhen, China","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100428136","display_name":"Yanfang Li","orcid":"https://orcid.org/0000-0002-1487-365X"},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuru Li","raw_affiliation_strings":["Department of Electronic and Electrical Engineering, Southern University of Science and Technology, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic and Electrical Engineering, Southern University of Science and Technology, Shenzhen, China","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126850615","display_name":"Yu Wei","orcid":null},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Wei","raw_affiliation_strings":["Department of Electronic and Electrical Engineering, Southern University of Science and Technology, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic and Electrical Engineering, Southern University of Science and Technology, Shenzhen, China","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126811979","display_name":"Qi Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Qi Wang","raw_affiliation_strings":["Department of Electronic and Electrical Engineering, University of British Columbia, Vancouver, BC, Canada"],"raw_orcid":"https://orcid.org/0000-0002-2644-2873","affiliations":[{"raw_affiliation_string":"Department of Electronic and Electrical Engineering, University of British Columbia, Vancouver, BC, Canada","institution_ids":["https://openalex.org/I141945490"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5122829117","display_name":"Terry Tao Ye","orcid":null},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Terry Tao Ye","raw_affiliation_strings":["Department of Science and Engineering, The Chinese University of Hong Kong, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-4359-3550","affiliations":[{"raw_affiliation_string":"Department of Science and Engineering, The Chinese University of Hong Kong, Shenzhen, China","institution_ids":["https://openalex.org/I4210116924"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.23000442,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"34","issue":"5","first_page":"1667","last_page":"1671"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.12759999930858612,"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"}},"topics":[{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.12759999930858612,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.08950000256299973,"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/T11417","display_name":"Advancements in PLL and VCO Technologies","score":0.06319999694824219,"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/multiplication","display_name":"Multiplication (music)","score":0.7186999917030334},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.6847000122070312},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6177999973297119},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.5745999813079834},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5620999932289124},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5133000016212463},{"id":"https://openalex.org/keywords/cmos","display_name":"CMOS","score":0.4952000081539154},{"id":"https://openalex.org/keywords/energy","display_name":"Energy (signal processing)","score":0.45320001244544983},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.4438999891281128}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7601000070571899},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.7186999917030334},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.6847000122070312},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6177999973297119},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.5745999813079834},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5620999932289124},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5133000016212463},{"id":"https://openalex.org/C46362747","wikidata":"https://www.wikidata.org/wiki/Q173431","display_name":"CMOS","level":2,"score":0.4952000081539154},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.45969998836517334},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.45320001244544983},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.4438999891281128},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.41780000925064087},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.41260001063346863},{"id":"https://openalex.org/C2778456923","wikidata":"https://www.wikidata.org/wiki/Q5337692","display_name":"Edge computing","level":3,"score":0.3578000068664551},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.35190001130104065},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.3513999879360199},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.3492000102996826},{"id":"https://openalex.org/C201290732","wikidata":"https://www.wikidata.org/wiki/Q130762","display_name":"Multiplication algorithm","level":3,"score":0.32510000467300415},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.31690001487731934},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.31619998812675476},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3043000102043152},{"id":"https://openalex.org/C157170001","wikidata":"https://www.wikidata.org/wiki/Q4781507","display_name":"Applications of artificial intelligence","level":2,"score":0.30410000681877136},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.29809999465942383},{"id":"https://openalex.org/C13164978","wikidata":"https://www.wikidata.org/wiki/Q600158","display_name":"Hardware acceleration","level":3,"score":0.2921999990940094},{"id":"https://openalex.org/C131017901","wikidata":"https://www.wikidata.org/wiki/Q170451","display_name":"Logic gate","level":2,"score":0.2824999988079071},{"id":"https://openalex.org/C165005293","wikidata":"https://www.wikidata.org/wiki/Q1074500","display_name":"Chip","level":2,"score":0.2777000069618225},{"id":"https://openalex.org/C157922185","wikidata":"https://www.wikidata.org/wiki/Q173198","display_name":"Logic synthesis","level":3,"score":0.2703999876976013},{"id":"https://openalex.org/C2780971903","wikidata":"https://www.wikidata.org/wiki/Q2933705","display_name":"Stochastic computing","level":3,"score":0.2685000002384186},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.2662000060081482},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.26420000195503235},{"id":"https://openalex.org/C530198007","wikidata":"https://www.wikidata.org/wiki/Q80831","display_name":"Integrated circuit","level":2,"score":0.26339998841285706},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2630999982357025},{"id":"https://openalex.org/C77390884","wikidata":"https://www.wikidata.org/wiki/Q217302","display_name":"Application-specific integrated circuit","level":2,"score":0.2524999976158142}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tvlsi.2026.3661565","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tvlsi.2026.3661565","pdf_url":null,"source":{"id":"https://openalex.org/S37538908","display_name":"IEEE Transactions on Very Large Scale Integration (VLSI) Systems","issn_l":"1063-8210","issn":["1063-8210","1557-9999"],"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 Very Large Scale Integration (VLSI) Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5918474793434143,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W2113994308","https://openalex.org/W2172654076","https://openalex.org/W2963255460","https://openalex.org/W2963881497","https://openalex.org/W3048933702","https://openalex.org/W3133079566","https://openalex.org/W3193967165","https://openalex.org/W3203242999","https://openalex.org/W4312298069","https://openalex.org/W4327522190","https://openalex.org/W4388581301","https://openalex.org/W4391547488","https://openalex.org/W4400811641","https://openalex.org/W4402426679"],"related_works":[],"abstract_inverted_index":{"The":[0,61,109],"rapid":[1],"evolution":[2],"of":[3,13,22,44,95,123],"artificial":[4],"intelligence":[5],"(AI)":[6],"in":[7,79,106,113,128],"IoT":[8],"applications":[9],"necessitates":[10],"the":[11,20,37,40,50,84,93,96,119,150,160],"execution":[12,151],"inference":[14,148],"tasks":[15],"on":[16,26,49],"edge":[17,28],"devices.":[18],"However,":[19],"deployment":[21],"computation-intensive":[23],"neural":[24,107,145],"networks":[25],"resource-constrained":[27],"systems":[29],"presents":[30,36],"a":[31,45,64,76,87,114],"significant":[32],"challenge.":[33],"This":[34],"brief":[35],"RV-WINO":[38,110],"processor,":[39],"first":[41],"silicon":[42],"implementation":[43],"RISC-V":[46],"processor":[47,62,85,111],"based":[48],"Winograd":[51,65,97],"algorithm":[52],"for":[53],"convolution":[54],"and":[55,102,125,130,140],"general":[56],"matrix":[57,88],"multiplication":[58,70,89],"(GEMM)":[59],"acceleration.":[60],"incorporates":[63],"module,":[66,98],"which":[67],"significantly":[68],"reduces":[69],"operations":[71,105],"during":[72],"convolutions,":[73],"leading":[74],"to":[75],"substantial":[77],"decrease":[78],"energy":[80,136],"consumption.":[81],"In":[82,143],"addition,":[83],"includes":[86],"module":[90],"that":[91],"reuses":[92],"multipliers":[94],"accelerating":[99],"fully":[100],"connected":[101],"dot":[103],"product":[104],"networks.":[108],"fabricated":[112],"55-nm":[115],"CMOS":[116],"process":[117],"achieves":[118],"peak":[120,135],"computational":[121],"performance":[122],"0.95":[124],"2.39":[126],"GOPS":[127],"INT32":[129],"INT8":[131],"modes,":[132],"with":[133,159],"its":[134],"efficiency":[137],"reaching":[138],"112":[139],"237":[141],"GOPS/W.":[142],"convolutional":[144],"network":[146],"(CNN)":[147],"tasks,":[149],"time":[152],"is":[153],"reduced":[154],"by":[155],"over":[156],"80%":[157],"compared":[158],"baseline":[161],"processor.":[162]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-02-26T00:00:00"}