{"id":"https://openalex.org/W2943187097","doi":"https://doi.org/10.1109/iscas.2019.8702547","title":"Smilodon: An Efficient Accelerator for Low Bit-Width CNNs with Task Partitioning","display_name":"Smilodon: An Efficient Accelerator for Low Bit-Width CNNs with Task Partitioning","publication_year":2019,"publication_date":"2019-05-01","ids":{"openalex":"https://openalex.org/W2943187097","doi":"https://doi.org/10.1109/iscas.2019.8702547","mag":"2943187097"},"language":"en","primary_location":{"id":"doi:10.1109/iscas.2019.8702547","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscas.2019.8702547","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Symposium on Circuits and Systems (ISCAS)","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/A5041745327","display_name":"Qinyu Chen","orcid":"https://orcid.org/0009-0005-9480-6164"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Qinyu Chen","raw_affiliation_strings":["School of Electronic Science and Engineering, Nanjing University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"School of Electronic Science and Engineering, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009522891","display_name":"Yuxiang Fu","orcid":"https://orcid.org/0000-0003-1351-5460"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuxiang Fu","raw_affiliation_strings":["School of Electronic Science and Engineering, Nanjing University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"School of Electronic Science and Engineering, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039185927","display_name":"Kaifeng Cheng","orcid":"https://orcid.org/0000-0003-2860-0932"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kaifeng Cheng","raw_affiliation_strings":["School of Electronic Science and Engineering, Nanjing University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"School of Electronic Science and Engineering, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035766448","display_name":"Wenqing Song","orcid":"https://orcid.org/0000-0002-8806-8717"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenqing Song","raw_affiliation_strings":["School of Electronic Science and Engineering, Nanjing University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"School of Electronic Science and Engineering, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072973899","display_name":"Zhonghai Lu","orcid":"https://orcid.org/0000-0003-0061-3475"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Zhonghai Lu","raw_affiliation_strings":["KTH-Royal Institute of Technology, Stockholm, Sweden"],"affiliations":[{"raw_affiliation_string":"KTH-Royal Institute of Technology, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100361096","display_name":"Li Li","orcid":"https://orcid.org/0000-0002-1047-6067"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Li","raw_affiliation_strings":["School of Electronic Science and Engineering, Nanjing University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"School of Electronic Science and Engineering, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100380082","display_name":"Chuan Zhang","orcid":"https://orcid.org/0000-0002-7736-6487"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chuan Zhang","raw_affiliation_strings":["School of Electronic Science and Engineering, Nanjing University, Nanjing, China","Lab of Efficient Architectures for Digital-communication and Signal-processing (LEADS)"],"affiliations":[{"raw_affiliation_string":"School of Electronic Science and Engineering, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]},{"raw_affiliation_string":"Lab of Efficient Architectures for Digital-communication and Signal-processing (LEADS)","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5041745327"],"corresponding_institution_ids":["https://openalex.org/I881766915"],"apc_list":null,"apc_paid":null,"fwci":0.3037,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.59035221,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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":0.9976999759674072,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9975000023841858,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8633170127868652},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.7109909653663635},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7103980183601379},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6675601005554199},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.6126964688301086},{"id":"https://openalex.org/keywords/frame-rate","display_name":"Frame rate","score":0.6106600165367126},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5811522006988525},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5341156125068665},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.4976032078266144},{"id":"https://openalex.org/keywords/hardware-acceleration","display_name":"Hardware acceleration","score":0.49622994661331177},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.44854068756103516},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.448064923286438},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.44601327180862427},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4386652112007141},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.421996533870697},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3819861114025116},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.35482269525527954},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32392144203186035},{"id":"https://openalex.org/keywords/wireless","display_name":"Wireless","score":0.1763400137424469},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1720188558101654},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.10716021060943604},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.10249146819114685}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8633170127868652},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.7109909653663635},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7103980183601379},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6675601005554199},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.6126964688301086},{"id":"https://openalex.org/C3261483","wikidata":"https://www.wikidata.org/wiki/Q119565","display_name":"Frame rate","level":2,"score":0.6106600165367126},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5811522006988525},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5341156125068665},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4976032078266144},{"id":"https://openalex.org/C13164978","wikidata":"https://www.wikidata.org/wiki/Q600158","display_name":"Hardware acceleration","level":3,"score":0.49622994661331177},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.44854068756103516},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.448064923286438},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.44601327180862427},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4386652112007141},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.421996533870697},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3819861114025116},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.35482269525527954},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32392144203186035},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.1763400137424469},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1720188558101654},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.10716021060943604},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.10249146819114685},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscas.2019.8702547","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscas.2019.8702547","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Symposium on Circuits and Systems (ISCAS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","score":0.699999988079071,"display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W47391476","https://openalex.org/W1922655562","https://openalex.org/W2158899491","https://openalex.org/W2163605009","https://openalex.org/W2276486856","https://openalex.org/W2289252105","https://openalex.org/W2319920447","https://openalex.org/W2466675884","https://openalex.org/W2469490737","https://openalex.org/W2513568085","https://openalex.org/W2520083297","https://openalex.org/W2604319603","https://openalex.org/W2625954420","https://openalex.org/W2761757071","https://openalex.org/W2762651727","https://openalex.org/W2776940252","https://openalex.org/W2802200896","https://openalex.org/W2889111331","https://openalex.org/W2952230511","https://openalex.org/W2997828269","https://openalex.org/W4387007199","https://openalex.org/W6640090968","https://openalex.org/W6683738474","https://openalex.org/W6684191040","https://openalex.org/W6700264148","https://openalex.org/W6720242923","https://openalex.org/W6747157835","https://openalex.org/W6856891780"],"related_works":["https://openalex.org/W2111241003","https://openalex.org/W2518118925","https://openalex.org/W3159273459","https://openalex.org/W2053477252","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],"Networks":[2],"(CNNs)":[3],"have":[4],"been":[5],"widely":[6],"applied":[7],"in":[8,35,137],"various":[9],"fields":[10],"such":[11],"as":[12],"image":[13],"and":[14,19,27,144],"video":[15],"recognition,":[16],"recommender":[17],"systems,":[18],"natural":[20],"language":[21],"processing.":[22],"However,":[23],"the":[24,39,85,105,124,134,138],"massive":[25],"size":[26],"intensive":[28],"computation":[29],"loads":[30],"prevent":[31],"its":[32],"feasible":[33],"deployment":[34],"practice,":[36],"especially":[37],"on":[38,71,98],"embedded":[40],"systems.":[41],"As":[42],"a":[43,62,72,78,110],"highly":[44],"competitive":[45],"candidate,":[46],"low":[47,67],"bit-width":[48,68],"CNNs":[49,69],"are":[50],"proposed":[51],"to":[52,133],"enable":[53],"efficient":[54,64],"implementation.":[55],"In":[56],"this":[57],"paper,":[58],"we":[59],"propose":[60],"Smilodon,":[61],"scalable,":[63],"accelerator":[65,130],"for":[66,91],"based":[70],"parallel":[73],"streaming":[74],"architecture,":[75],"optimized":[76],"with":[77,109],"task":[79],"partitioning":[80],"strategy.":[81],"We":[82],"also":[83],"present":[84],"3D":[86],"systolic-like":[87],"computing":[88],"arrays":[89],"fitting":[90],"convolutional":[92],"layers.":[93],"Our":[94],"design":[95],"is":[96,131],"implemented":[97],"Zynq":[99],"XC7Z020":[100],"FPGA,":[101],"which":[102],"can":[103],"satisfy":[104],"needs":[106],"of":[107,113,126],"real-time":[108],"frame":[111],"rate":[112],"1,":[114],"622":[115],"FPS":[116],"throughput,":[117,141],"while":[118],"consuming":[119],"2":[120],"1":[121],"Watt.":[122],"To":[123],"best":[125],"our":[127,129],"knowledge,":[128],"superior":[132],"state-of-the-art":[135],"works":[136],"tradeoff":[139],"among":[140],"power":[142],"efficiency,":[143],"area":[145],"efficiency.":[146]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}