{"id":"https://openalex.org/W2785545076","doi":"https://doi.org/10.1109/fpt.2017.8280147","title":"Instruction driven cross-layer CNN accelerator with winograd transformation on FPGA","display_name":"Instruction driven cross-layer CNN accelerator with winograd transformation on FPGA","publication_year":2017,"publication_date":"2017-12-01","ids":{"openalex":"https://openalex.org/W2785545076","doi":"https://doi.org/10.1109/fpt.2017.8280147","mag":"2785545076"},"language":"en","primary_location":{"id":"doi:10.1109/fpt.2017.8280147","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fpt.2017.8280147","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 International Conference on Field Programmable Technology (ICFPT)","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/A5112107807","display_name":"Jincheng Yu","orcid":"https://orcid.org/0009-0007-3831-3845"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jincheng Yu","raw_affiliation_strings":["Electronic Engineering Department, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Electronic Engineering Department, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102712817","display_name":"Yiming Hu","orcid":"https://orcid.org/0009-0006-2418-976X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiming Hu","raw_affiliation_strings":["Electronic Engineering Department, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Electronic Engineering Department, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086217226","display_name":"Xuefei Ning","orcid":"https://orcid.org/0000-0003-2209-8312"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuefei Ning","raw_affiliation_strings":["Electronic Engineering Department, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Electronic Engineering Department, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090846991","display_name":"Jiantao Qiu","orcid":"https://orcid.org/0000-0002-1328-2639"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiantao Qiu","raw_affiliation_strings":["Electronic Engineering Department, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Electronic Engineering Department, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101189530","display_name":"Kaiyuan Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kaiyuan Guo","raw_affiliation_strings":["Electronic Engineering Department, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Electronic Engineering Department, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100445368","display_name":"Yu Wang","orcid":"https://orcid.org/0000-0003-3511-0288"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Wang","raw_affiliation_strings":["Electronic Engineering Department, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Electronic Engineering Department, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023755254","display_name":"Huazhong Yang","orcid":"https://orcid.org/0000-0003-2421-353X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huazhong Yang","raw_affiliation_strings":["Electronic Engineering Department, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Electronic Engineering Department, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5112107807"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":2.0935,"has_fulltext":false,"cited_by_count":35,"citation_normalized_percentile":{"value":0.92828531,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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":0.9998999834060669,"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":0.9980999827384949,"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/loop-unrolling","display_name":"Loop unrolling","score":0.8921953439712524},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.8640742897987366},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8517205119132996},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6045523285865784},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5912764072418213},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.49899911880493164},{"id":"https://openalex.org/keywords/hardware-acceleration","display_name":"Hardware acceleration","score":0.4890921711921692},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.4384104311466217},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4379446506500244},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.37403303384780884},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.35317325592041016},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2908451557159424},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2267577052116394},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.22519221901893616},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.12475124001502991}],"concepts":[{"id":"https://openalex.org/C76970557","wikidata":"https://www.wikidata.org/wiki/Q1869750","display_name":"Loop unrolling","level":3,"score":0.8921953439712524},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.8640742897987366},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8517205119132996},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6045523285865784},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5912764072418213},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.49899911880493164},{"id":"https://openalex.org/C13164978","wikidata":"https://www.wikidata.org/wiki/Q600158","display_name":"Hardware acceleration","level":3,"score":0.4890921711921692},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.4384104311466217},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4379446506500244},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.37403303384780884},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.35317325592041016},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2908451557159424},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2267577052116394},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.22519221901893616},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.12475124001502991},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/fpt.2017.8280147","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fpt.2017.8280147","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 International Conference on Field Programmable Technology (ICFPT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8999999761581421,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1487564550","https://openalex.org/W1686810756","https://openalex.org/W2094756095","https://openalex.org/W2208299922","https://openalex.org/W2276486856","https://openalex.org/W2289252105","https://openalex.org/W2525740295","https://openalex.org/W2565305208","https://openalex.org/W2584311934","https://openalex.org/W2729080111","https://openalex.org/W4249932213"],"related_works":["https://openalex.org/W4225949190","https://openalex.org/W2964954556","https://openalex.org/W3019910406","https://openalex.org/W2518118925","https://openalex.org/W3035662153","https://openalex.org/W3159273459","https://openalex.org/W3213934210","https://openalex.org/W3212577482","https://openalex.org/W4281393566","https://openalex.org/W4367054505"],"abstract_inverted_index":{"In":[0,89],"recent":[1],"years,":[2],"Convolutional":[3],"Neural":[4],"Network":[5],"(CNN)":[6],"has":[7],"been":[8,17],"widely":[9,18],"applied":[10],"in":[11,37,132],"computer":[12],"vision":[13],"tasks.":[14],"FPGAs":[15],"have":[16],"explored":[19],"to":[20,24,113],"accelerate":[21],"CNNs":[22],"due":[23],"its":[25],"high":[26,28],"performance,":[27],"energy":[29],"efficiency,":[30],"and":[31,102,119,139],"flexibility.":[32],"By":[33],"fusing":[34],"multiple":[35],"layers":[36],"CNN,":[38],"the":[39,53,87,108,122,136,152,195],"intermediate":[40,153],"data":[41,154],"transfer":[42,155],"can":[43,57,156,200],"be":[44,58,79,157,201],"reduced.":[45],"With":[46],"a":[47,72,149,185],"faster":[48],"algorithm":[49,68,101],"using":[50],"Winograd":[51,67,100,208],"transformation,":[52],"computation":[54,128],"of":[55,171],"convolution":[56],"further":[59,202],"accelerated.":[60],"However,":[61],"previous":[62,190],"accelerators":[63],"with":[64,166],"cross-layer":[65,103,109,167,191],"or":[66],"are":[69,211],"designed":[70],"for":[71,126],"particular":[73],"CNN":[74,84,97,164],"model.":[75],"The":[76,169,198],"FPGA":[77,146,192],"should":[78],"reprogrammed":[80],"when":[81],"running":[82],"another":[83],"model":[85,165],"on":[86,142,162,194],"hardware.":[88],"this":[90],"work,":[91],"we":[92],"design":[93,183],"an":[94],"instruction":[95],"driven":[96],"accelerator":[98,174,193],"supporting":[99],"scheduling.":[104],"We":[105,134],"firstly":[106],"modify":[107],"loop":[110],"unrolling":[111],"order":[112],"extract":[114],"basic":[115],"operations":[116],"as":[117],"instructions,":[118],"then":[120],"improve":[121],"on-chip":[123],"memory":[124],"architecture":[125,138],"higher":[127],"units":[129],"utilization":[130],"rate":[131],"Winograd.":[133],"evaluate":[135],"hardware":[137,173],"scheduling":[140],"policy":[141],"Xilinx":[143],"Virtex-7":[144],"690t":[145],"platform.":[147,197],"As":[148],"case":[150],"study,":[151],"reduced":[158],"by":[159,204],"over":[160],"90%":[161],"VGG-D":[163],"policy.":[168],"performance":[170,199],"our":[172,182],"reaches":[175],"1500":[176],"GOP/s.":[177],"Experimental":[178],"results":[179],"show":[180],"that":[181],"achieves":[184],"7":[186],"\u03c7":[187],"speed-up":[188],"than":[189],"same":[196],"improved":[203],"78%":[205],"if":[206],"larger":[207],"transformation":[209],"sizes":[210],"used.":[212]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":11},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}