{"id":"https://openalex.org/W2627042741","doi":"https://doi.org/10.1145/3061639.3062244","title":"Exploring Heterogeneous Algorithms for Accelerating Deep Convolutional Neural Networks on FPGAs","display_name":"Exploring Heterogeneous Algorithms for Accelerating Deep Convolutional Neural Networks on FPGAs","publication_year":2017,"publication_date":"2017-06-13","ids":{"openalex":"https://openalex.org/W2627042741","doi":"https://doi.org/10.1145/3061639.3062244","mag":"2627042741"},"language":"en","primary_location":{"id":"doi:10.1145/3061639.3062244","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3061639.3062244","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 54th Annual Design Automation Conference 2017","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/A5057484285","display_name":"Qingcheng Xiao","orcid":"https://orcid.org/0000-0001-6230-5342"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingcheng Xiao","raw_affiliation_strings":["Center for Energy-efficient Computing and Applications, EECS, Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Energy-efficient Computing and Applications, EECS, Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100604860","display_name":"Yun Liang","orcid":"https://orcid.org/0000-0002-9076-7998"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yun Liang","raw_affiliation_strings":["Center for Energy-efficient Computing and Applications, EECS, Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Energy-efficient Computing and Applications, EECS, Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072265593","display_name":"Liqiang Lu","orcid":"https://orcid.org/0000-0002-3801-6847"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liqiang Lu","raw_affiliation_strings":["Center for Energy-efficient Computing and Applications, EECS, Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Energy-efficient Computing and Applications, EECS, Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049910854","display_name":"Shengen Yan","orcid":"https://orcid.org/0009-0005-3858-7972"},"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":"Shengen Yan","raw_affiliation_strings":["Department of Information Engineering, Chinese University of Hong Kong and SenseTime Group Limited"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information Engineering, Chinese University of Hong Kong and SenseTime Group Limited","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001987788","display_name":"Yu\u2010Wing Tai","orcid":"https://orcid.org/0000-0002-3148-0380"},"institutions":[{"id":"https://openalex.org/I4210128910","display_name":"Group Sense (China)","ror":"https://ror.org/036wd5777","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210128910"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu-Wing Tai","raw_affiliation_strings":["SenseTime Group Limited"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SenseTime Group Limited","institution_ids":["https://openalex.org/I4210128910"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":208,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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":0.9998000264167786,"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":0.9998000264167786,"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":0.9994999766349792,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9994999766349792,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.840173602104187},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.7625762224197388},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7127393484115601},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.6103436946868896},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.600536584854126},{"id":"https://openalex.org/keywords/toolchain","display_name":"Toolchain","score":0.5260750651359558},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.5186325907707214},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.41795945167541504},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41359788179397583},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4133099615573883},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3532307744026184},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3506682515144348},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.2136797308921814},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.1265316903591156},{"id":"https://openalex.org/keywords/wireless","display_name":"Wireless","score":0.1189018189907074}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.840173602104187},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.7625762224197388},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7127393484115601},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.6103436946868896},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.600536584854126},{"id":"https://openalex.org/C2777062904","wikidata":"https://www.wikidata.org/wiki/Q545406","display_name":"Toolchain","level":3,"score":0.5260750651359558},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.5186325907707214},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.41795945167541504},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41359788179397583},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4133099615573883},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3532307744026184},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3506682515144348},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.2136797308921814},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.1265316903591156},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.1189018189907074},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3061639.3062244","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3061639.3062244","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 54th Annual Design Automation Conference 2017","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.41999998688697815,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1005811612","https://openalex.org/W1487564550","https://openalex.org/W1686810756","https://openalex.org/W1935978687","https://openalex.org/W1983364832","https://openalex.org/W2002555321","https://openalex.org/W2009832130","https://openalex.org/W2015332951","https://openalex.org/W2053968820","https://openalex.org/W2094756095","https://openalex.org/W2097117768","https://openalex.org/W2152839228","https://openalex.org/W2155893237","https://openalex.org/W2166029537","https://openalex.org/W2172654076","https://openalex.org/W2276486856","https://openalex.org/W2285660444","https://openalex.org/W2396572963","https://openalex.org/W2403646140","https://openalex.org/W2442974303","https://openalex.org/W2565305208","https://openalex.org/W2618530766","https://openalex.org/W2729080111","https://openalex.org/W2906043559","https://openalex.org/W2950656546","https://openalex.org/W2963000224","https://openalex.org/W2963981420","https://openalex.org/W2964299589","https://openalex.org/W4249932213"],"related_works":["https://openalex.org/W2013037783","https://openalex.org/W2909413202","https://openalex.org/W1999008563","https://openalex.org/W4385243142","https://openalex.org/W2561644314","https://openalex.org/W2794118724","https://openalex.org/W2912135124","https://openalex.org/W4206450104","https://openalex.org/W2076915000","https://openalex.org/W3157543420"],"abstract_inverted_index":{"Convolutional":[0],"neural":[1],"network":[2],"(CNN)":[3],"finds":[4],"applications":[5,12],"in":[6,87],"a":[7,43,78,107],"variety":[8],"of":[9,106],"computer":[10],"vision":[11],"ranging":[13],"from":[14,56,134],"object":[15],"recognition":[16],"and":[17,118,148],"detection":[18],"to":[19,23,102,114,130,137,156,161],"scene":[20],"understanding":[21],"owing":[22],"its":[24],"exceptional":[25],"accuracy.":[26],"There":[27],"exist":[28],"different":[29],"algorithms":[30,101],"for":[31,51,121,167],"CNNs":[32],"computation.":[33],"In":[34],"this":[35,95],"paper,":[36],"we":[37,98],"explore":[38,99],"conventional":[39,58],"convolution":[40,59],"algorithm":[41,45,62,113,119],"with":[42],"faster":[44],"using":[46,140,144],"Winograd's":[47],"minimal":[48],"filtering":[49],"theory":[50],"efficient":[52],"FPGA":[53,138,165],"implementation.":[54],"Distinct":[55],"the":[57,72,90,104,116,132,162],"algorithm,":[60],"Winograd":[61],"uses":[63],"less":[64],"computing":[65],"resources":[66],"but":[67],"puts":[68],"more":[69],"pressure":[70],"on":[71,94],"memory":[73],"bandwidth.":[74],"We":[75,109,124],"first":[76],"propose":[77],"fusion":[79,96,117],"architecture":[80],"that":[81,151],"can":[82],"fuse":[83],"multiple":[84],"layers":[85],"naturally":[86],"CNNs,":[88],"reusing":[89],"intermediate":[91],"data.":[92],"Based":[93],"architecture,":[97],"heterogeneous":[100],"maximize":[103],"throughput":[105],"CNN.":[108],"design":[110,153],"an":[111,127],"optimal":[112],"determine":[115],"strategy":[120],"each":[122],"layer.":[123],"also":[125],"develop":[126],"automated":[128],"toolchain":[129],"ease":[131],"mapping":[133],"Caffe":[135],"model":[136],"bitstream":[139],"Vivado":[141],"HLS.":[142],"Experiments":[143],"widely":[145],"used":[146],"VGG":[147],"AlexNet":[149],"demonstrate":[150],"our":[152],"achieves":[154],"up":[155],"1.99X":[157],"performance":[158],"speedup":[159],"compared":[160],"prior":[163],"fusion-based":[164],"accelerator":[166],"CNNs.":[168]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":22},{"year":2022,"cited_by_count":22},{"year":2021,"cited_by_count":35},{"year":2020,"cited_by_count":35},{"year":2019,"cited_by_count":42},{"year":2018,"cited_by_count":27},{"year":2017,"cited_by_count":5}],"updated_date":"2026-07-20T07:56:41.581041","created_date":"2025-10-10T00:00:00"}