{"id":"https://openalex.org/W4404133961","doi":"https://doi.org/10.1145/3649329.3657392","title":"WinoGen: A Highly Configurable Winograd Convolution IP Generator for Efficient CNN Acceleration on FPGA","display_name":"WinoGen: A Highly Configurable Winograd Convolution IP Generator for Efficient CNN Acceleration on FPGA","publication_year":2024,"publication_date":"2024-06-23","ids":{"openalex":"https://openalex.org/W4404133961","doi":"https://doi.org/10.1145/3649329.3657392"},"language":"en","primary_location":{"id":"doi:10.1145/3649329.3657392","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3649329.3657392","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 61st ACM/IEEE Design Automation Conference","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3649329.3657392","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5086203449","display_name":"Mingjun Li","orcid":"https://orcid.org/0009-0007-6740-8413"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Mingjun Li","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong, Hong Kong, Hong Kong Special Administrative Region of China"],"raw_orcid":"https://orcid.org/0009-0007-6740-8413","affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong, Hong Kong, Hong Kong Special Administrative Region of China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083471412","display_name":"Pengjia Li","orcid":"https://orcid.org/0009-0005-1580-6714"},"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":"Pengjia Li","raw_affiliation_strings":["The Chinese University of Hong Kong, Shenzhen, Guangdong, China"],"raw_orcid":"https://orcid.org/0009-0005-1580-6714","affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Shenzhen, Guangdong, China","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101319284","display_name":"Shuo Yin","orcid":"https://orcid.org/0000-0003-4927-0194"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Shuo Yin","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong, Hong Kong, Hong Kong Special Administrative Region of China"],"raw_orcid":"https://orcid.org/0000-0003-4927-0194","affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong, Hong Kong, Hong Kong Special Administrative Region of China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071519571","display_name":"Shixin Chen","orcid":"https://orcid.org/0000-0002-9401-0482"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Shixin Chen","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong, Hong Kong, Hong Kong Special Administrative Region of China"],"raw_orcid":"https://orcid.org/0000-0002-9401-0482","affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong, Hong Kong, Hong Kong Special Administrative Region of China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114860550","display_name":"Beichen Li","orcid":"https://orcid.org/0009-0003-5989-2998"},"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":"Beichen Li","raw_affiliation_strings":["The Chinese University of Hong Kong, Shenzhen, Guangdong, China"],"raw_orcid":"https://orcid.org/0009-0003-5989-2998","affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Shenzhen, Guangdong, China","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109906206","display_name":"C. H. Tong","orcid":"https://orcid.org/0009-0007-7442-8957"},"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":"Chong Tong","raw_affiliation_strings":["The Chinese University of Hong Kong, Shenzhen, Guangdong, China"],"raw_orcid":"https://orcid.org/0009-0007-7442-8957","affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Shenzhen, Guangdong, China","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053303853","display_name":"Jianlei Yang","orcid":"https://orcid.org/0000-0001-8424-7040"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianlei Yang","raw_affiliation_strings":["Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-8424-7040","affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022945347","display_name":"Tinghuan Chen","orcid":"https://orcid.org/0000-0002-9195-6619"},"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":"Tinghuan Chen","raw_affiliation_strings":["The Chinese University of Hong Kong, Shenzhen, Guangdong, China"],"raw_orcid":"https://orcid.org/0000-0002-9195-6619","affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Shenzhen, Guangdong, China","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051340429","display_name":"Bei Yu","orcid":"https://orcid.org/0000-0001-6406-4810"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Bei Yu","raw_affiliation_strings":["The Chinese University of Hong Kong, Shatin, Hong Kong Special Administrative Region of China"],"raw_orcid":"https://orcid.org/0000-0001-6406-4810","affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Shatin, Hong Kong Special Administrative Region of China","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":9,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9155,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.75234606,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"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/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.9983000159263611,"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/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.9983000159263611,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9976000189781189,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9955000281333923,"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/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.8224923610687256},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.7604413628578186},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7512580752372742},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.6816077828407288},{"id":"https://openalex.org/keywords/acceleration","display_name":"Acceleration","score":0.6750677824020386},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4276338517665863},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.41254955530166626},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.3899945318698883},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.21616417169570923},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.06715092062950134}],"concepts":[{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.8224923610687256},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.7604413628578186},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7512580752372742},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.6816077828407288},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.6750677824020386},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4276338517665863},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.41254955530166626},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.3899945318698883},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.21616417169570923},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.06715092062950134},{"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},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0},{"id":"https://openalex.org/C74650414","wikidata":"https://www.wikidata.org/wiki/Q11397","display_name":"Classical mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3649329.3657392","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3649329.3657392","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 61st ACM/IEEE Design Automation Conference","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3649329.3657392","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3649329.3657392","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 61st ACM/IEEE Design Automation Conference","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","score":0.8299999833106995,"display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W2172654076","https://openalex.org/W2899915146","https://openalex.org/W2941408718","https://openalex.org/W2964525696","https://openalex.org/W2997109118","https://openalex.org/W3091969046","https://openalex.org/W3193946904","https://openalex.org/W3215698464","https://openalex.org/W3217077065"],"related_works":["https://openalex.org/W2111241003","https://openalex.org/W2355315220","https://openalex.org/W4200391368","https://openalex.org/W2210979487","https://openalex.org/W2316202402","https://openalex.org/W2074043759","https://openalex.org/W2082487009","https://openalex.org/W2373535795","https://openalex.org/W2565094479","https://openalex.org/W3103262449"],"abstract_inverted_index":{"The":[0],"convolution":[1,20,40,74],"neural":[2],"network":[3],"(CNN)":[4],"has":[5],"been":[6],"widely":[7],"adopted":[8],"in":[9],"computer":[10],"vision":[11],"tasks.":[12],"In":[13],"the":[14,110],"FPGA-based":[15],"CNN":[16,139],"accelerator":[17],"design,":[18],"Winograd":[19,39,57,62,73],"can":[21,86,96],"effectively":[22],"improve":[23],"computation":[24],"performance":[25],"and":[26,33,53,82,103,122,132],"save":[27],"hardware":[28],"resources.":[29],"However,":[30],"building":[31],"efficient":[32,54],"highly":[34,71],"compatible":[35,98],"IP":[36,75,90,95,111],"for":[37],"arbitrary":[38,78],"on":[41],"FPGA":[42],"remains":[43],"underexplored.":[44],"To":[45],"address":[46],"this":[47],"issue,":[48],"we":[49],"propose":[50],"a":[51,69,137],"novel":[52],"reformulation":[55],"of":[56],"convolution,":[58],"named":[59],"Structured":[60],"Direct":[61],"Convolution":[63],"(SDW).":[64],"We":[65],"further":[66],"develop":[67],"WinoGen,":[68],"Chisel-based":[70],"configurable":[72],"generator.":[76],"Given":[77],"input/output":[79],"tile":[80,104],"size":[81],"kernel":[83,101],"size,":[84],"it":[85],"generate":[87],"optimized":[88],"high-performance":[89],"automatically.":[91],"Meanwhile,":[92],"our":[93],"generated":[94,112],"be":[97],"with":[99,142],"multiple":[100],"sizes":[102],"sizes.":[105],"Experimental":[106],"results":[107],"show":[108],"that":[109],"by":[113],"WinoGen":[114],"achieves":[115],"DSP":[116],"efficiency":[117,124],"up":[118,125],"to":[119,126],"3.80":[120],"GOPS/DSP":[121],"energy":[123],"652.77":[127],"GOPS/W":[128],"while":[129],"showing":[130],"2.45\u00d7":[131],"3.10\u00d7":[133],"improvements":[134],"when":[135],"processing":[136],"same":[138],"model":[140],"compared":[141],"state-of-the-arts.":[143]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4}],"updated_date":"2026-06-19T17:40:00.097472","created_date":"2025-10-10T00:00:00"}