{"id":"https://openalex.org/W3198625877","doi":"https://doi.org/10.1109/tc.2021.3110413","title":"OctCNN: A High Throughput FPGA Accelerator for CNNs using Octave Convolution Algorithm","display_name":"OctCNN: A High Throughput FPGA Accelerator for CNNs using Octave Convolution Algorithm","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3198625877","doi":"https://doi.org/10.1109/tc.2021.3110413","mag":"3198625877"},"language":"en","primary_location":{"id":"doi:10.1109/tc.2021.3110413","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tc.2021.3110413","pdf_url":null,"source":{"id":"https://openalex.org/S157670870","display_name":"IEEE Transactions on Computers","issn_l":"0018-9340","issn":["0018-9340","0016-9340","1557-9956","2326-3814"],"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 Computers","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":"https://openalex.org/A5034765006","display_name":"Wenqi Lou","orcid":"https://orcid.org/0000-0002-2240-6672"},"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":"Wenqi Lou","raw_affiliation_strings":["School of Computer Science, University of Science and Technology of China, 12652 Hefei, Anhui, China, (e-mail: louwenqi@mail.ustc.edu.cn)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Science and Technology of China, 12652 Hefei, Anhui, China, (e-mail: louwenqi@mail.ustc.edu.cn)","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072915437","display_name":"Lei Gong","orcid":"https://orcid.org/0000-0002-8391-5526"},"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":"Lei Gong","raw_affiliation_strings":["School of Computer Science, University of Science and Technology of China, 12652 Hefei, Anhui, China, 230026 (e-mail: leigong0203@ustc.edu.cn)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Science and Technology of China, 12652 Hefei, Anhui, China, 230026 (e-mail: leigong0203@ustc.edu.cn)","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":["Computer Science, University of Science and Technology of China, 12652 Hefei, Anhui, China, 230026 (e-mail: cswang@ustc.edu.cn)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science, University of Science and Technology of China, 12652 Hefei, Anhui, China, 230026 (e-mail: cswang@ustc.edu.cn)","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056949827","display_name":"Zidong Du","orcid":"https://orcid.org/0000-0002-7603-4210"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zidong Du","raw_affiliation_strings":["State Key Laboratory of Computer Architecture, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, Beijing, China, 100190 (e-mail: duzidong@ict.ac.cn)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Computer Architecture, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, Beijing, China, 100190 (e-mail: duzidong@ict.ac.cn)","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}]},{"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":"Zhou Xuehai","raw_affiliation_strings":["Computer Science Department, University of Science and Technology of China, Hefei, Anhui, China, (e-mail: xhzhou@ustc.edu.cn)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, University of Science and Technology of China, Hefei, Anhui, China, (e-mail: xhzhou@ustc.edu.cn)","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.8159,"has_fulltext":false,"cited_by_count":36,"citation_normalized_percentile":{"value":0.86065762,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"1"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":1.0,"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":1.0,"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":0.9980000257492065,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9948999881744385,"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":0.8207747936248779},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.764347493648529},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6481130123138428},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.6436896324157715},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.6071528196334839},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6024026870727539},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.5841108560562134},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5330871939659119},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.44851237535476685},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.3257523775100708},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.29653945565223694},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.20065847039222717},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.16339445114135742}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8207747936248779},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.764347493648529},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6481130123138428},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.6436896324157715},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.6071528196334839},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6024026870727539},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.5841108560562134},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5330871939659119},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.44851237535476685},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3257523775100708},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.29653945565223694},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.20065847039222717},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.16339445114135742},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tc.2021.3110413","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tc.2021.3110413","pdf_url":null,"source":{"id":"https://openalex.org/S157670870","display_name":"IEEE Transactions on Computers","issn_l":"0018-9340","issn":["0018-9340","0016-9340","1557-9956","2326-3814"],"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 Computers","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4603026834","display_name":null,"funder_award_id":"No. 61976200","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W1600744878","https://openalex.org/W1686810756","https://openalex.org/W2048266589","https://openalex.org/W2067523571","https://openalex.org/W2094756095","https://openalex.org/W2097117768","https://openalex.org/W2172654076","https://openalex.org/W2194775991","https://openalex.org/W2285660444","https://openalex.org/W2442974303","https://openalex.org/W2466675884","https://openalex.org/W2469490737","https://openalex.org/W2565125333","https://openalex.org/W2584616277","https://openalex.org/W2616014673","https://openalex.org/W2626112510","https://openalex.org/W2729080111","https://openalex.org/W2792503273","https://openalex.org/W2795961274","https://openalex.org/W2796160902","https://openalex.org/W2891946740","https://openalex.org/W2899915146","https://openalex.org/W2901214301","https://openalex.org/W2902895686","https://openalex.org/W2903778355","https://openalex.org/W2913221350","https://openalex.org/W2917087921","https://openalex.org/W2944824859","https://openalex.org/W2963037989","https://openalex.org/W2988396473","https://openalex.org/W3005712428","https://openalex.org/W3034653380","https://openalex.org/W3093799822","https://openalex.org/W3096298715","https://openalex.org/W3101086546","https://openalex.org/W3112948415","https://openalex.org/W4212788319","https://openalex.org/W4302296459","https://openalex.org/W6637151318","https://openalex.org/W6637373629","https://openalex.org/W6720242923"],"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/W2157978810","https://openalex.org/W2076915000","https://openalex.org/W3157543420"],"abstract_inverted_index":{"With":[0],"the":[1,14,27,41,46,51,56,78,93,104,137,155,164,175],"rapid":[2],"development":[3],"of":[4,13,80,151],"convolutional":[5,156],"neural":[6],"networks":[7],"(CNNs),":[8],"FPGAs":[9],"have":[10],"become":[11],"one":[12],"most":[15],"attractive":[16],"candidates":[17],"for":[18,50,65,154,158,163],"deploying":[19],"CNNs.":[20],"However,":[21],"previous":[22,171],"FPGA":[23],"solutions":[24],"based":[25,121,173],"on":[26,122,136,174],"traditional":[28,176],"convolution":[29,43],"are":[30],"still":[31],"limited":[32],"by":[33,131],"computational":[34,195],"power.":[35],"In":[36],"this":[37],"article,":[38],"we":[39,83,107],"introduce":[40],"octave":[42],"(OctConv)":[44],"into":[45],"CNN":[47],"accelerator":[48],"design":[49,61,198],"first":[52],"time":[53],"to":[54,68,76,102,170,183,191],"improve":[55],"hardware":[57],"acceleration":[58],"efficiency":[59],"and":[60,87,97,112,116,124,134,160,188,205],"a":[62,72,85,109,117,181,189],"dedicated":[63],"OctPU":[64],"mapping":[66],"OctConv":[67],"FPGAs,":[69],"which":[70],"employs":[71],"parallel":[73],"dataflow":[74],"pattern":[75],"exploit":[77],"parallelism":[79],"OctConv.":[81,168],"Then,":[82],"present":[84],"novel":[86],"scalable":[88],"architecture":[89],"that":[90,144],"dynamically":[91],"combines":[92],"inter-layer":[94],"pipelined":[95],"structure":[96],"multi-layer":[98],"reuse":[99],"structure.":[100],"Meanwhile,":[101],"obtain":[103],"optimized":[105],"solution,":[106],"build":[108],"multidimensional":[110],"performance":[111,204],"resource":[113],"analysis":[114],"model":[115],"two-stage":[118],"search":[119],"algorithm":[120],"greedy":[123],"heuristic":[125],"algorithms.":[126],"We":[127],"evaluate":[128],"our":[129,145,178],"proposal":[130],"implementing":[132],"VGG16":[133,159],"ResNet50":[135,166],"Xilinx":[138],"VU9P":[139],"FPGA.":[140],"Experimental":[141],"results":[142],"show":[143],"prototypes":[146,179],"can":[147],"achieve":[148],"an":[149,201],"average":[150],"3321":[152],"GOP/s":[153,162],"layers":[157],"2873":[161],"overall":[165],"using":[167],"Compared":[169],"works":[172],"convolution,":[177],"own":[180],"1.72":[182],"2.33":[184],"speedup":[185],"in":[186,194],"throughput":[187],"2.01":[190],"5.18":[192],"improvement":[193],"density.":[196],"Our":[197],"also":[199],"presents":[200],"excellent":[202],"compromise":[203],"generalization":[206]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":15},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":2}],"updated_date":"2026-08-04T08:18:43.703281","created_date":"2025-10-10T00:00:00"}
