{"id":"https://openalex.org/W2525740295","doi":"https://doi.org/10.1109/fpl.2016.7577308","title":"A high performance FPGA-based accelerator for large-scale convolutional neural networks","display_name":"A high performance FPGA-based accelerator for large-scale convolutional neural networks","publication_year":2016,"publication_date":"2016-08-01","ids":{"openalex":"https://openalex.org/W2525740295","doi":"https://doi.org/10.1109/fpl.2016.7577308","mag":"2525740295"},"language":"en","primary_location":{"id":"doi:10.1109/fpl.2016.7577308","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fpl.2016.7577308","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 26th International Conference on Field Programmable Logic and Applications (FPL)","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/A5039504617","display_name":"Huimin Li","orcid":"https://orcid.org/0000-0001-7494-6745"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huimin Li","raw_affiliation_strings":["State Key Laboratory of ASIC and System, Fudan University Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of ASIC and System, Fudan University Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066019284","display_name":"Xitian Fan","orcid":"https://orcid.org/0000-0001-8698-6584"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xitian Fan","raw_affiliation_strings":["State Key Laboratory of ASIC and System, Fudan University Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of ASIC and System, Fudan University Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074284592","display_name":"Jiao Li","orcid":"https://orcid.org/0000-0001-6391-8343"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Jiao","raw_affiliation_strings":["State Key Laboratory of ASIC and System, Fudan University Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of ASIC and System, Fudan University Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100694034","display_name":"Wei Cao","orcid":"https://orcid.org/0000-0003-0339-7093"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Cao","raw_affiliation_strings":["State Key Laboratory of ASIC and System, Fudan University Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of ASIC and System, Fudan University Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103281733","display_name":"Xuegong Zhou","orcid":"https://orcid.org/0000-0003-4178-4094"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuegong Zhou","raw_affiliation_strings":["State Key Laboratory of ASIC and System, Fudan University Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of ASIC and System, Fudan University Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002732486","display_name":"Lingli Wang","orcid":"https://orcid.org/0000-0002-0579-3527"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lingli Wang","raw_affiliation_strings":["State Key Laboratory of ASIC and System, Fudan University Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of ASIC and System, Fudan University Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I24943067"],"apc_list":null,"apc_paid":null,"fwci":12.0773,"has_fulltext":false,"cited_by_count":310,"citation_normalized_percentile":{"value":0.98954482,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"9"},"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":0.9997000098228455,"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/computer-science","display_name":"Computer science","score":0.8656983375549316},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7959655523300171},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.7127606272697449},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.6552461981773376},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5681294202804565},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.56264328956604},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.5076495409011841},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.45078200101852417},{"id":"https://openalex.org/keywords/high-memory","display_name":"High memory","score":0.4430209994316101},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.43535757064819336},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4169030487537384},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3981218934059143},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.3600393533706665},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3505714237689972},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.26004138588905334},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.13219451904296875},{"id":"https://openalex.org/keywords/wireless","display_name":"Wireless","score":0.1097712516784668},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.08401718735694885}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8656983375549316},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7959655523300171},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.7127606272697449},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.6552461981773376},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5681294202804565},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.56264328956604},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.5076495409011841},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.45078200101852417},{"id":"https://openalex.org/C2781357197","wikidata":"https://www.wikidata.org/wiki/Q5757597","display_name":"High memory","level":2,"score":0.4430209994316101},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.43535757064819336},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4169030487537384},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3981218934059143},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3600393533706665},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3505714237689972},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.26004138588905334},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.13219451904296875},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.1097712516784668},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.08401718735694885},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/fpl.2016.7577308","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fpl.2016.7577308","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 26th International Conference on Field Programmable Logic and Applications (FPL)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1549036680","https://openalex.org/W1594170634","https://openalex.org/W1686810756","https://openalex.org/W1841592590","https://openalex.org/W1983364832","https://openalex.org/W1990315422","https://openalex.org/W1995562189","https://openalex.org/W1998808035","https://openalex.org/W2000967104","https://openalex.org/W2009832130","https://openalex.org/W2048266589","https://openalex.org/W2053968820","https://openalex.org/W2067523571","https://openalex.org/W2094756095","https://openalex.org/W2096645269","https://openalex.org/W2112796928","https://openalex.org/W2117539524","https://openalex.org/W2117696986","https://openalex.org/W2144172034","https://openalex.org/W2152839228","https://openalex.org/W2155893237","https://openalex.org/W2163605009","https://openalex.org/W2276486856","https://openalex.org/W2294282016","https://openalex.org/W2504108613","https://openalex.org/W2963374099","https://openalex.org/W3004171485","https://openalex.org/W4247470470","https://openalex.org/W4248707617","https://openalex.org/W6635557998","https://openalex.org/W6637373629","https://openalex.org/W6638783484","https://openalex.org/W6674479107","https://openalex.org/W6681239517","https://openalex.org/W6684191040","https://openalex.org/W6694717790"],"related_works":["https://openalex.org/W4243474409","https://openalex.org/W2058636218","https://openalex.org/W2993780376","https://openalex.org/W2607256436","https://openalex.org/W2114927422","https://openalex.org/W2528745529","https://openalex.org/W1966777863","https://openalex.org/W3145767355","https://openalex.org/W2739266613","https://openalex.org/W4200309432"],"abstract_inverted_index":{"In":[0,89],"recent":[1],"years,":[2],"convolutional":[3],"neural":[4],"networks":[5],"(CNNs)":[6],"based":[7],"machine":[8],"learning":[9],"algorithms":[10],"have":[11,29],"been":[12],"widely":[13],"applied":[14,98],"in":[15,59],"computer":[16],"vision":[17],"applications.":[18],"However,":[19],"for":[20,76],"large-scale":[21,140],"CNNs,":[22],"the":[23,46,65,72,107,113,126],"computation-intensive,":[24],"memory-intensive":[25,114],"and":[26,85,97,157],"resource-consuming":[27],"features":[28],"brought":[30],"many":[31],"challenges":[32],"to":[33,63,81,105,112],"CNN":[34,42],"implementations.":[35],"This":[36],"work":[37,57],"proposes":[38],"an":[39],"end-to-end":[40],"FPGA-based":[41],"accelerator":[43],"with":[44],"all":[45],"layers":[47,55,102],"mapped":[48],"on":[49,99,123,145],"one":[50],"chip":[51],"so":[52],"that":[53],"different":[54,120],"can":[56,70,130,149],"concurrently":[58],"a":[60,91,135,138,151],"pipelined":[61],"structure":[62],"increase":[64,106],"throughput.":[66],"A":[67],"methodology":[68],"which":[69,164],"find":[71],"optimized":[73],"parallelism":[74],"strategy":[75],"each":[77],"layer":[78],"is":[79,95,143],"proposed":[80],"achieve":[82,150],"high":[83,86],"throughput":[84],"resource":[87],"utilization.":[88],"addition,":[90],"batch-based":[92],"computing":[93,121],"method":[94],"implemented":[96,144],"fully":[100],"connected":[101],"(FC":[103],"layers)":[104],"memory":[108],"bandwidth":[109],"utilization":[110],"due":[111],"feature.":[115],"Further,":[116],"by":[117],"applying":[118],"two":[119],"patterns":[122],"FC":[124],"layers,":[125],"required":[127],"on-chip":[128],"buffers":[129],"be":[131],"reduced":[132],"significantly.":[133],"As":[134],"case":[136],"study,":[137],"state-of-the-art":[139],"CNN,":[141],"AlexNet,":[142],"Xilinx":[146],"VC709.":[147],"It":[148],"peak":[152],"performance":[153],"of":[154],"565.94":[155],"GOP/s":[156],"391":[158],"FPS":[159],"under":[160],"156MHz":[161],"clock":[162],"frequency":[163],"outperforms":[165],"previous":[166],"approaches.":[167]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":20},{"year":2023,"cited_by_count":23},{"year":2022,"cited_by_count":36},{"year":2021,"cited_by_count":44},{"year":2020,"cited_by_count":51},{"year":2019,"cited_by_count":53},{"year":2018,"cited_by_count":44},{"year":2017,"cited_by_count":22},{"year":2016,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}