{"id":"https://openalex.org/W3008408165","doi":"https://doi.org/10.1145/3373087.3375311","title":"Light-OPU","display_name":"Light-OPU","publication_year":2020,"publication_date":"2020-02-23","ids":{"openalex":"https://openalex.org/W3008408165","doi":"https://doi.org/10.1145/3373087.3375311","mag":"3008408165"},"language":"en","primary_location":{"id":"doi:10.1145/3373087.3375311","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3373087.3375311","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays","raw_type":"proceedings-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":["University of California, Los Angeles, Los Angeles, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Los Angeles, Los Angeles, CA, 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":["University of California, Los Angeles, Los Angeles, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Los Angeles, Los Angeles, CA, 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":["University of California, Los Angeles, Los Angeles, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Los Angeles, Los Angeles, CA, 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":["University of California, Los Angeles, Los Angeles, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Los Angeles, Los Angeles, CA, 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":5.9714,"has_fulltext":false,"cited_by_count":98,"citation_normalized_percentile":{"value":0.97173636,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"122","last_page":"132"},"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9979000091552734,"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"}},{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9962000250816345,"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":0.7612392902374268},{"id":"https://openalex.org/keywords/hardware-acceleration","display_name":"Hardware acceleration","score":0.6811135411262512},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.6689212322235107},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5868241786956787},{"id":"https://openalex.org/keywords/control-reconfiguration","display_name":"Control reconfiguration","score":0.569807767868042},{"id":"https://openalex.org/keywords/acceleration","display_name":"Acceleration","score":0.5625295042991638},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4792509078979492},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.4764276444911957},{"id":"https://openalex.org/keywords/electrical-efficiency","display_name":"Electrical efficiency","score":0.42950788140296936},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.36121225357055664},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.3322945237159729},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.3279606103897095},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.2465789020061493},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.18310695886611938}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7612392902374268},{"id":"https://openalex.org/C13164978","wikidata":"https://www.wikidata.org/wiki/Q600158","display_name":"Hardware acceleration","level":3,"score":0.6811135411262512},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.6689212322235107},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5868241786956787},{"id":"https://openalex.org/C119701452","wikidata":"https://www.wikidata.org/wiki/Q5165881","display_name":"Control reconfiguration","level":2,"score":0.569807767868042},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.5625295042991638},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4792509078979492},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.4764276444911957},{"id":"https://openalex.org/C118993495","wikidata":"https://www.wikidata.org/wiki/Q5042828","display_name":"Electrical efficiency","level":3,"score":0.42950788140296936},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.36121225357055664},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3322945237159729},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.3279606103897095},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.2465789020061493},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.18310695886611938},{"id":"https://openalex.org/C74650414","wikidata":"https://www.wikidata.org/wiki/Q11397","display_name":"Classical mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3373087.3375311","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3373087.3375311","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5600000023841858,"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W1990315422","https://openalex.org/W2053968820","https://openalex.org/W2094756095","https://openalex.org/W2097117768","https://openalex.org/W2183341477","https://openalex.org/W2194775991","https://openalex.org/W2272300165","https://openalex.org/W2276486856","https://openalex.org/W2279098554","https://openalex.org/W2294282016","https://openalex.org/W2520083297","https://openalex.org/W2531409750","https://openalex.org/W2559085405","https://openalex.org/W2562773490","https://openalex.org/W2625954420","https://openalex.org/W2761085955","https://openalex.org/W2789333991","https://openalex.org/W2790621718","https://openalex.org/W2796160902","https://openalex.org/W2804032941","https://openalex.org/W2810861508","https://openalex.org/W2883780447","https://openalex.org/W2887936511","https://openalex.org/W2897049076","https://openalex.org/W2897655610","https://openalex.org/W2901214301","https://openalex.org/W2911374887","https://openalex.org/W2951433694","https://openalex.org/W2955542801","https://openalex.org/W2962761403","https://openalex.org/W2963125010","https://openalex.org/W2963163009","https://openalex.org/W2963256077","https://openalex.org/W2963741033","https://openalex.org/W2979455536","https://openalex.org/W2982083293","https://openalex.org/W3004171485","https://openalex.org/W3101086546","https://openalex.org/W3102633758"],"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/W2103526090","https://openalex.org/W1574948540"],"abstract_inverted_index":{"Lightweight":[0],"convolutional":[1],"neural":[2],"networks":[3],"(LW-CNNs)":[4],"such":[5],"as":[6],"MobileNet,":[7],"ShuffleNet,":[8],"SqueezeNet,":[9],"etc.,":[10],"have":[11],"emerged":[12],"in":[13],"the":[14,106,178,185,210],"past":[15],"few":[16],"years":[17],"for":[18,52,70,84,193],"fast":[19],"inference":[20],"on":[21,137,153,189],"embedded":[22],"and":[23,40,80,100,110,124,148,199],"mobile":[24],"system.":[25],"However,":[26],"lightweight":[27,82],"operations":[28,83,99],"limit":[29],"acceleration":[30,195],"potential":[31],"by":[32],"GPU":[33,158],"due":[34],"to":[35,48,166],"their":[36,41],"memory":[37],"bounded":[38],"nature":[39],"parallel":[42],"mechanisms":[43],"that":[44,142],"are":[45],"not":[46],"friendly":[47],"SIMD.":[49],"This":[50,104],"calls":[51],"more":[53],"specific":[54],"accelerators.":[55,176],"In":[56],"this":[57],"paper,":[58],"we":[59],"propose":[60],"an":[61],"FPGA-based":[62,190],"overlay":[63],"processor":[64,192],"with":[65,156,172,196],"a":[66],"corresponding":[67],"compilation":[68],"flow":[69],"general":[71,191],"LW-CNN":[72],"accelerations,":[73],"called":[74],"Light-OPU.":[75],"Software-hardware":[76],"co-designed":[77],"Light-OPU":[78,115,143,163,183],"reformulates":[79],"decomposes":[81],"efficient":[85],"acceleration.":[86],"Moreover,":[87],"our":[88,181],"instruction":[89],"architecture":[90],"considers":[91],"sharing":[92],"of":[93,121,129,180],"major":[94,139,207],"computation":[95],"engine":[96],"between":[97],"LW":[98],"conventional":[101],"convolution":[102],"operations.":[103],"improves":[105],"run-time":[107],"resource":[108],"efficiency":[109,152,170],"overall":[111],"power":[112,151,169,200],"efficiency.":[113],"Finally,":[114],"is":[116,184,203],"software":[117],"programmable,":[118],"since":[119],"loading":[120],"compiled":[122],"codes":[123],"kernel":[125],"weights":[126],"completes":[127],"switch":[128],"targeted":[130],"network":[131],"without":[132],"FPGA":[133,175],"reconfiguration.":[134],"Our":[135],"experiments":[136],"seven":[138],"LW-CNNs":[140,194,208],"show":[141],"achieves":[144],"5.5x":[145],"better":[146,168],"latency":[147],"3.0x":[149],"higher":[150],"average":[154],"compared":[155,171],"edge":[157],"NVIDIA":[159],"Jetson":[160],"TX2.":[161],"Furthermore,":[162],"has":[164],"1.3x":[165],"8.4x":[167],"previous":[173],"customized":[174],"To":[177],"best":[179],"knowledge,":[182],"first":[186],"in-depth":[187],"study":[188],"high":[197],"performance":[198],"efficiency,":[201],"which":[202],"evaluated":[204],"using":[205],"all":[206],"including":[209],"newly":[211],"released":[212],"MobileNetV3.":[213]},"counts_by_year":[{"year":2025,"cited_by_count":17},{"year":2024,"cited_by_count":20},{"year":2023,"cited_by_count":15},{"year":2022,"cited_by_count":23},{"year":2021,"cited_by_count":19},{"year":2020,"cited_by_count":4}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2020-03-06T00:00:00"}