{"id":"https://openalex.org/W3034100311","doi":"https://doi.org/10.1109/tvlsi.2020.2995741","title":"<i>Uni-OPU</i>: An FPGA-Based Uniform Accelerator for Convolutional and Transposed Convolutional Networks","display_name":"<i>Uni-OPU</i>: An FPGA-Based Uniform Accelerator for Convolutional and Transposed Convolutional Networks","publication_year":2020,"publication_date":"2020-06-02","ids":{"openalex":"https://openalex.org/W3034100311","doi":"https://doi.org/10.1109/tvlsi.2020.2995741","mag":"3034100311"},"language":"en","primary_location":{"id":"doi:10.1109/tvlsi.2020.2995741","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tvlsi.2020.2995741","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/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/A5100350102","display_name":"Mingyu Wang","orcid":"https://orcid.org/0000-0001-5722-9752"},"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":"Mingyu 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":"middle","author":{"id":"https://openalex.org/A5100366737","display_name":"Kun Wang","orcid":"https://orcid.org/0000-0003-4180-6150"},"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":3.5382,"has_fulltext":false,"cited_by_count":53,"citation_normalized_percentile":{"value":0.93428995,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"28","issue":"7","first_page":"1545","last_page":"1556"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9941999912261963,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9941999912261963,"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":0.9930999875068665,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9898999929428101,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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":0.7298264503479004},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5637556314468384},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.54805588722229},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.4516226649284363}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7298264503479004},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5637556314468384},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.54805588722229},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.4516226649284363},{"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:10.1109/tvlsi.2020.2995741","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tvlsi.2020.2995741","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":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.8700000047683716}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W1885185971","https://openalex.org/W1901129140","https://openalex.org/W1903029394","https://openalex.org/W2067523571","https://openalex.org/W2155893237","https://openalex.org/W2173520492","https://openalex.org/W2276486856","https://openalex.org/W2304648132","https://openalex.org/W2331128040","https://openalex.org/W2402144811","https://openalex.org/W2503339013","https://openalex.org/W2520707372","https://openalex.org/W2525167219","https://openalex.org/W2526009326","https://openalex.org/W2535388113","https://openalex.org/W2546066744","https://openalex.org/W2598581049","https://openalex.org/W2613577722","https://openalex.org/W2798838583","https://openalex.org/W2891976760","https://openalex.org/W2895738878","https://openalex.org/W2899824860","https://openalex.org/W2906403229","https://openalex.org/W2914366177","https://openalex.org/W2951939904","https://openalex.org/W2953384591","https://openalex.org/W2962793481","https://openalex.org/W2963577671","https://openalex.org/W2963684088","https://openalex.org/W2963985284","https://openalex.org/W2964024144","https://openalex.org/W2964231161","https://openalex.org/W2979455536","https://openalex.org/W4247470470","https://openalex.org/W6639824700","https://openalex.org/W6685352114","https://openalex.org/W6697974390","https://openalex.org/W6713134421","https://openalex.org/W6727553916","https://openalex.org/W6729001083","https://openalex.org/W6735204497","https://openalex.org/W6737901870","https://openalex.org/W6758990815"],"related_works":["https://openalex.org/W2778498407","https://openalex.org/W2317245370","https://openalex.org/W4249323025","https://openalex.org/W198851386","https://openalex.org/W1980160788","https://openalex.org/W2030310580","https://openalex.org/W947442053","https://openalex.org/W2148915962","https://openalex.org/W2283866686","https://openalex.org/W2948365806"],"abstract_inverted_index":{"In":[0,206],"this":[1],"article,":[2],"we":[3,208],"design":[4],"the":[5,40,57,63,79,142,197,237,244,251],"first":[6,245],"full":[7],"software/":[8],"hardware":[9,17,119,123],"stack,":[10],"called":[11],"Uni-OPU,":[12],"for":[13,141],"an":[14],"efficient":[15,109],"uniform":[16,99,132],"acceleration":[18,124,189,198],"of":[19,22,42,71,78,82,159,199,239,254],"different":[20,164],"types":[21],"transposed":[23],"convolutional":[24,29],"(TCONV)":[25],"networks":[26,116,162,228],"and":[27,53,87,90,103,107,111,211,219,226,257],"conventional":[28],"(CONV)":[30],"networks.":[31],"Specifically,":[32],"a":[33,98,118,155],"software":[34],"compiler":[35,61],"is":[36,126,173,191,243],"provided":[37],"to":[38,69,114,128,138,175,178,248],"transform":[39],"computation":[41,133,252],"various":[43],"TCONV,":[44],"i.e.,":[45],"zero-inserting-based":[46],"TCONV":[47,51,74,83,89,143,161],"(zero-TCONV),":[48],"nearest-neighbor":[49],"resizing-based":[50],"(NN-TCONV),":[52],"CONV":[54,91,258],"layers":[55],"into":[56,92],"same":[58],"pattern.":[59],"The":[60],"conducts":[62],"following":[64],"optimizations:":[65],"1)":[66],"eliminating":[67],"up":[68,137],"98.4%":[70],"operations":[72],"in":[73],"by":[75],"making":[76],"use":[77],"fixed":[80],"pattern":[81,134],"upsampling;":[84],"2)":[85],"decomposing":[86],"reformulating":[88],"streaming":[93],"parallel":[94],"vector":[95],"multiplication":[96],"with":[97,135,184,230],"address":[100],"generation":[101],"scheme":[102],"data":[104],"flow":[105],"pattern;":[106],"3)":[108],"scheduling":[110],"instruction":[112],"compilation":[113],"map":[115],"onto":[117],"processor.":[120],"An":[121],"instruction-based":[122],"processor":[125],"developed":[127],"efficiently":[129],"speedup":[130],"our":[131,240],"throughput":[136],"2.35":[139],"TOPS":[140],"layer,":[144],"consuming":[145],"only":[146],"2.89":[147],"W":[148],"dynamic":[149],"power.":[150],"We":[151],"evaluate":[152],"Uni-OPU":[153,172],"on":[154,194,224,234],"benchmark":[156],"set":[157],"composed":[158],"six":[160],"from":[163],"application":[165],"fields.":[166],"Extensive":[167],"experimental":[168],"results":[169],"indicate":[170],"that":[171],"able":[174],"gain":[176],"1.45\u00d7":[177],"3.68\u00d7":[179],"superior":[180],"power":[181,222],"efficiency":[182,223],"compared":[183,229],"state-of-the-art":[185],"zero-TCONV":[186,225],"accelerators.":[187],"High":[188],"performance":[190],"also":[192],"achieved":[193],"NN-TCONV":[195,227],"networks,":[196],"which":[200],"have":[201],"not":[202],"been":[203],"explored":[204],"before.":[205],"summary,":[207],"observe":[209],"1.90\u00d7":[210],"1.63\u00d7":[212],"latency":[213],"reduction,":[214],"as":[215,217],"well":[216],"15.04\u00d7":[218],"12.43\u00d7":[220],"higher":[221],"Titan":[231],"Xp":[232],"GPU":[233],"average.":[235],"To":[236],"best":[238],"knowledge,":[241],"ours":[242],"in-depth":[246],"study":[247],"completely":[249],"unify":[250],"process":[253],"zero-TCONV,":[255],"NN-TCONV,":[256],"layers.":[259]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":16},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":2}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}