{"id":"https://openalex.org/W2979455536","doi":"https://doi.org/10.1109/tvlsi.2019.2939726","title":"OPU: An FPGA-Based Overlay Processor for Convolutional Neural Networks","display_name":"OPU: An FPGA-Based Overlay Processor for Convolutional Neural Networks","publication_year":2019,"publication_date":"2019-10-08","ids":{"openalex":"https://openalex.org/W2979455536","doi":"https://doi.org/10.1109/tvlsi.2019.2939726","mag":"2979455536"},"language":"en","primary_location":{"id":"doi:10.1109/tvlsi.2019.2939726","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tvlsi.2019.2939726","pdf_url":null,"source":{"id":"https://openalex.org/S37538908","display_name":"IEEE Transactions on Very Large Scale Integration (VLSI) Systems","issn_l":"1063-8210","issn":["1063-8210","1557-9999"],"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 Very Large Scale Integration (VLSI) Systems","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/A5030145593","display_name":"Yunxuan Yu","orcid":"https://orcid.org/0000-0003-2605-8174"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yunxuan Yu","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of California at Los Angeles, Los Angeles, USA"],"raw_orcid":"https://orcid.org/0000-0003-2605-8174","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of California at Los Angeles, Los Angeles, USA","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100707380","display_name":"Chen Wu","orcid":"https://orcid.org/0000-0002-2492-0640"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chen Wu","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of California at Los Angeles, Los Angeles, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of California at Los Angeles, Los Angeles, USA","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073130132","display_name":"Tiandong Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tiandong Zhao","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of California at Los Angeles, Los Angeles, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of California at Los Angeles, Los Angeles, USA","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100366662","display_name":"Kun Wang","orcid":"https://orcid.org/0000-0002-4794-2359"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kun Wang","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of California at Los Angeles, Los Angeles, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of California at Los Angeles, Los Angeles, USA","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008695429","display_name":"Lei He","orcid":"https://orcid.org/0000-0002-5266-3805"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lei He","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of California at Los Angeles, Los Angeles, USA"],"raw_orcid":"https://orcid.org/0000-0002-5266-3805","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of California at Los Angeles, Los Angeles, USA","institution_ids":["https://openalex.org/I161318765"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I161318765"],"apc_list":null,"apc_paid":null,"fwci":5.6573,"has_fulltext":false,"cited_by_count":149,"citation_normalized_percentile":{"value":0.96849446,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"28","issue":"1","first_page":"35","last_page":"47"},"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/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"}},{"id":"https://openalex.org/T12676","display_name":"Machine Learning and ELM","score":0.9980000257492065,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.8653125762939453},{"id":"https://openalex.org/keywords/control-reconfiguration","display_name":"Control reconfiguration","score":0.7204132080078125},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.6662101149559021},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5968547463417053},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.5737850069999695},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5004127025604248},{"id":"https://openalex.org/keywords/compile-time","display_name":"Compile time","score":0.45297542214393616},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.37205591797828674},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.34557080268859863},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1624162197113037},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.10831370949745178}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8653125762939453},{"id":"https://openalex.org/C119701452","wikidata":"https://www.wikidata.org/wiki/Q5165881","display_name":"Control reconfiguration","level":2,"score":0.7204132080078125},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.6662101149559021},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5968547463417053},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.5737850069999695},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5004127025604248},{"id":"https://openalex.org/C200833197","wikidata":"https://www.wikidata.org/wiki/Q333707","display_name":"Compile time","level":3,"score":0.45297542214393616},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.37205591797828674},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.34557080268859863},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1624162197113037},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.10831370949745178}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tvlsi.2019.2939726","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tvlsi.2019.2939726","pdf_url":null,"source":{"id":"https://openalex.org/S37538908","display_name":"IEEE Transactions on Very Large Scale Integration (VLSI) Systems","issn_l":"1063-8210","issn":["1063-8210","1557-9999"],"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 Very Large Scale Integration (VLSI) Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8999999761581421,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W1836465849","https://openalex.org/W1990315422","https://openalex.org/W2009832130","https://openalex.org/W2053968820","https://openalex.org/W2094756095","https://openalex.org/W2163605009","https://openalex.org/W2183341477","https://openalex.org/W2194775991","https://openalex.org/W2272300165","https://openalex.org/W2276486856","https://openalex.org/W2294282016","https://openalex.org/W2402144811","https://openalex.org/W2520083297","https://openalex.org/W2523838129","https://openalex.org/W2562773490","https://openalex.org/W2570343428","https://openalex.org/W2584311934","https://openalex.org/W2616014673","https://openalex.org/W2625954420","https://openalex.org/W2627042741","https://openalex.org/W2761085955","https://openalex.org/W2899915146","https://openalex.org/W2949117887","https://openalex.org/W2953384591","https://openalex.org/W2962835968","https://openalex.org/W2963511748","https://openalex.org/W4242577057","https://openalex.org/W4387007199","https://openalex.org/W6637373629","https://openalex.org/W6638667902","https://openalex.org/W6674479107","https://openalex.org/W6684191040","https://openalex.org/W6713134421","https://openalex.org/W6727533809","https://openalex.org/W6731892127","https://openalex.org/W6856891780"],"related_works":["https://openalex.org/W2808484818","https://openalex.org/W2135053878","https://openalex.org/W2941434274","https://openalex.org/W2340647897","https://openalex.org/W4249632163","https://openalex.org/W2797161794","https://openalex.org/W2096938998","https://openalex.org/W1760305469","https://openalex.org/W1574948540","https://openalex.org/W2103526090"],"abstract_inverted_index":{"Field-programmable":[0],"gate":[1],"array":[2],"(FPGA)":[3],"provides":[4],"rich":[5],"parallel":[6],"computing":[7,241,251],"resources":[8],"with":[9,37,150,224,239],"high":[10],"energy":[11],"efficiency,":[12],"making":[13],"it":[14],"ideal":[15],"for":[16,66,89,113,137,201],"deep":[17,40],"convolutional":[18],"neural":[19],"network":[20,82],"(CNN)":[21],"acceleration.":[22],"In":[23,93,215],"recent":[24],"years,":[25],"automatic":[26],"compilers":[27],"have":[28,147],"been":[29],"developed":[30],"to":[31,105,163,173],"generate":[32],"network-specific":[33,57,70,210],"FPGA":[34,50,100,136],"accelerators.":[35],"However,":[36],"more":[38],"cascading":[39],"CNN":[41,90,107,114,118,142,231],"algorithms":[42,119],"adapted":[43],"by":[44,131],"various":[45],"complicated":[46,148],"tasks,":[47],"reconfiguration":[48,62,134],"of":[49,74,135,141,159,186,250],"devices":[51],"during":[52],"runtime":[53,188],"becomes":[54],"unavoidable":[55],"when":[56],"accelerators":[58,211],"are":[59,120,127],"employed.":[60],"Such":[61],"can":[63,182],"be":[64],"difficult":[65],"edge":[67,240],"devices.":[68],"Moreover,":[69,200],"accelerator":[71],"means":[72],"regeneration":[73],"RTL":[75],"code":[76],"and":[77,129,167,176,190,203],"physical":[78],"implementation":[79],"whenever":[80],"the":[81,213],"is":[83,86,161,235],"updated.":[84],"This":[85],"not":[87],"easy":[88],"end":[91,115],"users.":[92],"this":[94],"article,":[95],"we":[96],"propose":[97],"a":[98,154,228,247],"domain-specific":[99],"overlay":[101],"processor,":[102],"named":[103],"OPU":[104,132,145,181,206,217,234],"accelerate":[106],"networks.":[108,143,199],"It":[109],"offers":[110],"software-like":[111],"programmability":[112],"users,":[116],"as":[117],"automatically":[121,208],"compiled":[122,209],"into":[123],"executable":[124],"codes,":[125],"which":[126,245],"loaded":[128],"executed":[130],"without":[133],"switch":[138],"or":[139],"update":[140],"Our":[144],"instructions":[146],"functions":[149],"variable":[151],"runtimes":[152],"but":[153],"uniform":[155],"length.":[156],"The":[157],"granularity":[158],"instruction":[160],"optimized":[162],"provide":[164],"good":[165],"performance":[166],"sufficient":[168],"flexibility,":[169],"while":[170],"reducing":[171],"complexity":[172],"develop":[174],"microarchitecture":[175],"compiler.":[177],"Experiments":[178],"show":[179],"that":[180],"achieve":[183],"an":[184],"average":[185],"91%":[187],"multiplication":[189],"accumulation":[191],"unit":[192],"(MAC)":[193],"efficiency":[194,222],"(RME)":[195],"among":[196],"nine":[197],"different":[198],"VGG":[202],"YOLO":[204],"networks,":[205],"outperforms":[207],"in":[212],"literature.":[214],"addition,":[216],"shows":[218],"5.35\u00d7":[219],"better":[220],"power":[221],"compared":[223,238],"Titan":[225],"Xp.":[226],"For":[227],"real-time":[229],"cascaded":[230],"networks":[232],"scenario,":[233],"2.9\u00d7":[236],"faster":[237],"GPU":[242],"Jetson":[243],"Tx2,":[244],"has":[246],"similar":[248],"amount":[249],"resources.":[252]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":26},{"year":2024,"cited_by_count":29},{"year":2023,"cited_by_count":32},{"year":2022,"cited_by_count":25},{"year":2021,"cited_by_count":17},{"year":2020,"cited_by_count":14},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-11T18:08:03.149640","created_date":"2025-10-10T00:00:00"}