{"id":"https://openalex.org/W4322764670","doi":"https://doi.org/10.1145/3580219.3580227","title":"Research and Optimization of Neural Network Accelerator Based on NVDLA","display_name":"Research and Optimization of Neural Network Accelerator Based on NVDLA","publication_year":2023,"publication_date":"2023-01-28","ids":{"openalex":"https://openalex.org/W4322764670","doi":"https://doi.org/10.1145/3580219.3580227"},"language":"en","primary_location":{"id":"doi:10.1145/3580219.3580227","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3580219.3580227","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 7th International Conference on Control Engineering and Artificial Intelligence","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/A5069776729","display_name":"Liang Liu","orcid":"https://orcid.org/0000-0003-3794-0891"},"institutions":[{"id":"https://openalex.org/I4210089056","display_name":"Beijing Microelectronics Technology Institute","ror":"https://ror.org/007y7ej30","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210089056"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Liang Liu","raw_affiliation_strings":["BeiJing SmartChip Microelectronics Technology Company Limited, China"],"affiliations":[{"raw_affiliation_string":"BeiJing SmartChip Microelectronics Technology Company Limited, China","institution_ids":["https://openalex.org/I4210089056"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002163471","display_name":"Zengmin Ren","orcid":"https://orcid.org/0000-0002-9051-2717"},"institutions":[{"id":"https://openalex.org/I4210089056","display_name":"Beijing Microelectronics Technology Institute","ror":"https://ror.org/007y7ej30","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210089056"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zengmin Ren","raw_affiliation_strings":["BeiJing SmartChip Microelectronics Technology Company Limited, China"],"affiliations":[{"raw_affiliation_string":"BeiJing SmartChip Microelectronics Technology Company Limited, China","institution_ids":["https://openalex.org/I4210089056"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003307742","display_name":"Ting Chong","orcid":null},"institutions":[{"id":"https://openalex.org/I4210089056","display_name":"Beijing Microelectronics Technology Institute","ror":"https://ror.org/007y7ej30","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210089056"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ting Chong","raw_affiliation_strings":["BeiJing SmartChip Microelectronics Technology Company Limited, China"],"affiliations":[{"raw_affiliation_string":"BeiJing SmartChip Microelectronics Technology Company Limited, China","institution_ids":["https://openalex.org/I4210089056"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5069776729"],"corresponding_institution_ids":["https://openalex.org/I4210089056"],"apc_list":null,"apc_paid":null,"fwci":0.1235,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.35928366,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"37","last_page":"42"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9995999932289124,"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":0.9995999932289124,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.995199978351593,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9891999959945679,"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":0.8389649391174316},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.6817640066146851},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6433699727058411},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.6305060386657715},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6222934722900391},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.6146122217178345},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4790007770061493},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.4782756268978119},{"id":"https://openalex.org/keywords/hardware-acceleration","display_name":"Hardware acceleration","score":0.4578927457332611},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.4086422324180603},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3537423014640808},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.34144848585128784},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3269917368888855},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.320171058177948},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.19511616230010986}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8389649391174316},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.6817640066146851},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6433699727058411},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.6305060386657715},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6222934722900391},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.6146122217178345},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4790007770061493},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.4782756268978119},{"id":"https://openalex.org/C13164978","wikidata":"https://www.wikidata.org/wiki/Q600158","display_name":"Hardware acceleration","level":3,"score":0.4578927457332611},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.4086422324180603},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3537423014640808},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.34144848585128784},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3269917368888855},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.320171058177948},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.19511616230010986}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3580219.3580227","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3580219.3580227","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 7th International Conference on Control Engineering and Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W2097117768","https://openalex.org/W2155893237","https://openalex.org/W2194775991","https://openalex.org/W2583383421","https://openalex.org/W2618530766","https://openalex.org/W2769923865","https://openalex.org/W2895540242","https://openalex.org/W2963125010","https://openalex.org/W3177525997","https://openalex.org/W4237249260","https://openalex.org/W4238845948","https://openalex.org/W4248886231","https://openalex.org/W6725739302"],"related_works":["https://openalex.org/W3096456556","https://openalex.org/W4240253816","https://openalex.org/W2518118925","https://openalex.org/W3159273459","https://openalex.org/W4319952061","https://openalex.org/W4280636456","https://openalex.org/W4388913998","https://openalex.org/W4310584535","https://openalex.org/W4295935044","https://openalex.org/W3159906349"],"abstract_inverted_index":{"Convolutional":[0],"neural":[1,45,174],"network":[2,46,103,155,175,215,242],"(CNN)":[3],"has":[4,57],"been":[5],"widely":[6],"used":[7],"in":[8,38],"image":[9],"recognition":[10],"and":[11,17,31,62,101,170,185,187,228,244,250,257,280],"natural":[12],"language":[13],"processing.":[14],"Its":[15],"computing":[16],"storage":[18],"overhead":[19],"are":[20,37,262],"also":[21,87,235],"increased":[22],"with":[23,89],"the":[24,80,93,102,120,143,147,153,158,163,168,189,192,195,202,218,224,230,241,247,251,254,258,266],"advent":[25],"of":[26,29,82,95,146,162,172,183,204,208,221,226,270],"massive":[27],"amounts":[28],"data":[30,159,231,245,267],"complex":[32],"models,":[33],"Neural":[34],"processing":[35,219],"accelerators":[36],"urgent":[39],"need.":[40],"NVDLA":[41,196,227],"is":[42,65,70,86,99,108,211,275],"a":[43,179,237],"convolutional":[44],"accelerator":[47,197],"developed":[48],"by":[49,213,277],"NVIDIA":[50],"company":[51],"for":[52,73],"deep":[53],"learning":[54],"reasoning.":[55,272],"It":[56],"very":[58,71,109],"good":[59],"acceleration":[60,181],"performance,":[61],"its":[63],"code":[64],"completely":[66],"open":[67],"source,":[68],"which":[69,200],"helpful":[72],"our":[74],"in-depth":[75],"research.":[76],"However,":[77],"due":[78],"to":[79,151,156,216,264],"lack":[81],"multi-functional":[83],"tools,":[84],"DLA":[85],"faced":[88],"great":[90],"limitations.":[91],"Firstly,":[92],"number":[94],"operators":[96],"it":[97,105,112],"supports":[98],"insufficient,":[100],"model":[104,243],"can":[106,113,123,129],"support":[107,125,131],"limited,":[110],"so":[111],"only":[114,124],"realize":[115],"simple":[116],"classification":[117],"function;":[118],"Secondly,":[119],"official":[121],"compiler":[122],"Caffe":[126],"framework,":[127],"but":[128],"not":[130],"some":[132],"current":[133],"mainstream":[134],"frameworks,":[135],"such":[136],"as":[137],"pytorch,":[138],"tensorflow,":[139],"etc;":[140],"Finally,":[141,253],"before":[142],"hardware":[144,271],"reasoning":[145],"network,":[148],"we":[149,177],"need":[150],"quantify":[152],"designed":[154,263],"meet":[157],"format":[160],"requirements":[161,269],"hardware.":[164],"This":[165],"paper":[166],"explores":[167],"research":[169],"optimization":[171],"NVDLA-based":[173],"accelerators,":[176],"design":[178,236],"heterogeneous":[180,209],"system":[182,274],"FPGA":[184],"CPU,":[186,222],"Let":[188],"CPU":[190],"handle":[191],"parts":[193],"that":[194],"cannot":[198],"handle,":[199],"expands":[201],"function":[203],"NVDLA.The":[205],"task":[206],"division":[207],"operation":[210],"implemented":[212],"segmenting":[214],"minimize":[217,229],"part":[220],"thusmprove":[223],"utilization":[225],"communication":[232],"overhead.":[233],"We":[234],"conversion":[238],"method":[239],"between":[240],"under":[246],"common":[248],"framework":[249],"Caffe.":[252],"quantization":[255,259],"interface":[256],"calibration":[260],"table":[261],"meets":[265],"bit":[268],"The":[273],"verified":[276],"LeNet-5,":[278],"ResNet-50":[279],"YOLOv3.":[281]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-25T21:42:39.735039","created_date":"2025-10-10T00:00:00"}