{"id":"https://openalex.org/W2900158633","doi":"https://doi.org/10.1109/codesisss.2018.8525909","title":"Work-in-Progress: WinoNN: Optimising FPGA-based Neural Network Accelerators using Fast Winograd Algorithm","display_name":"Work-in-Progress: WinoNN: Optimising FPGA-based Neural Network Accelerators using Fast Winograd Algorithm","publication_year":2018,"publication_date":"2018-09-01","ids":{"openalex":"https://openalex.org/W2900158633","doi":"https://doi.org/10.1109/codesisss.2018.8525909","mag":"2900158633"},"language":"en","primary_location":{"id":"doi:10.1109/codesisss.2018.8525909","is_oa":false,"landing_page_url":"https://doi.org/10.1109/codesisss.2018.8525909","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 International Conference on Hardware/Software Codesign and System Synthesis (CODES+ISSS)","raw_type":"proceedings-article"},"type":"conference-paper","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":null,"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":null,"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":null,"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":3.1172,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.92667631,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"2"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9987000226974487,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.996999979019165,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.8780026435852051},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8218042850494385},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.6946618556976318},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6413365602493286},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5405473113059998},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4759906530380249},{"id":"https://openalex.org/keywords/loop-unrolling","display_name":"Loop unrolling","score":0.465046763420105},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.45517802238464355},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4368603825569153},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.43131023645401},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.4165636897087097},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.37991878390312195},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3604997992515564},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.24049648642539978},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.15831902623176575},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.09620407223701477},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.08583855628967285}],"concepts":[{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.8780026435852051},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8218042850494385},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.6946618556976318},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6413365602493286},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5405473113059998},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4759906530380249},{"id":"https://openalex.org/C76970557","wikidata":"https://www.wikidata.org/wiki/Q1869750","display_name":"Loop unrolling","level":3,"score":0.465046763420105},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.45517802238464355},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4368603825569153},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.43131023645401},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.4165636897087097},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.37991878390312195},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3604997992515564},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.24049648642539978},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.15831902623176575},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.09620407223701477},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.08583855628967285}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/codesisss.2018.8525909","is_oa":false,"landing_page_url":"https://doi.org/10.1109/codesisss.2018.8525909","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 International Conference on Hardware/Software Codesign and System Synthesis (CODES+ISSS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","score":0.49000000953674316,"display_name":"Decent work and economic growth"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1983364832","https://openalex.org/W2097117768","https://openalex.org/W2112796928","https://openalex.org/W2163605009","https://openalex.org/W2172654076","https://openalex.org/W2591882361","https://openalex.org/W2729080111","https://openalex.org/W6684191040","https://openalex.org/W6733960312"],"related_works":["https://openalex.org/W2058965144","https://openalex.org/W2164382479","https://openalex.org/W98480971","https://openalex.org/W2150291671","https://openalex.org/W2027972911","https://openalex.org/W2146343568","https://openalex.org/W2013643406","https://openalex.org/W2121492601","https://openalex.org/W3157543420","https://openalex.org/W1188123746"],"abstract_inverted_index":{"In":[0,17],"this":[1,45],"paper,":[2],"we":[3],"present":[4],"WinoNN,":[5],"which":[6,73],"utilizes":[7],"fast":[8],"Winograd":[9,19],"algorithm":[10,20],"to":[11],"optimize":[12],"FPGA-based":[13],"neural":[14],"network":[15],"accelerators.":[16],"particular,":[18],"effectively":[21],"reduces":[22],"the":[23,32,75,83],"resource":[24],"occupation":[25],"of":[26,44,49,54,77],"FPGA,":[27],"as":[28,30,69],"well":[29],"boosts":[31],"system":[33],"speedup,":[34],"especially":[35],"for":[36],"embedded":[37],"and":[38,59],"mobile":[39],"devices.":[40],"The":[41],"main":[42],"contributions":[43],"paper":[46],"include":[47],"implementation":[48,53],"single-channel":[50],"convolution":[51,56],"module,":[52,57],"multi-channel":[55],"deployment":[58],"performance":[60,76],"test":[61],"on":[62],"FPGA":[63],"hardware":[64],"platform.":[65],"We":[66],"use":[67],"LeNet-5":[68],"a":[70],"case":[71],"study,":[72],"demonstrates":[74],"WinoNN":[78],"is":[79],"significantly":[80],"better":[81],"than":[82],"general":[84],"ARM":[85],"Cortex":[86],"A":[87],"series":[88],"processors.":[89]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":6}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}