{"id":"https://openalex.org/W2973613048","doi":"https://doi.org/10.1109/tc.2019.2941875","title":"Fast and Efficient Convolutional Accelerator for Edge Computing","display_name":"Fast and Efficient Convolutional Accelerator for Edge Computing","publication_year":2019,"publication_date":"2019-09-16","ids":{"openalex":"https://openalex.org/W2973613048","doi":"https://doi.org/10.1109/tc.2019.2941875","mag":"2973613048"},"language":"en","primary_location":{"id":"doi:10.1109/tc.2019.2941875","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tc.2019.2941875","pdf_url":null,"source":{"id":"https://openalex.org/S157670870","display_name":"IEEE Transactions on Computers","issn_l":"0018-9340","issn":["0018-9340","1557-9956","2326-3814"],"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 Computers","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/A5064497251","display_name":"Arash Ardakani","orcid":"https://orcid.org/0000-0003-3274-2394"},"institutions":[{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Arash Ardakani","raw_affiliation_strings":["Electrical and Computer Engineering Department, McGill University, Montreal, Canada"],"raw_orcid":"https://orcid.org/0000-0003-3274-2394","affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering Department, McGill University, Montreal, Canada","institution_ids":["https://openalex.org/I5023651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085812448","display_name":"Carlo Condo","orcid":"https://orcid.org/0000-0002-3050-036X"},"institutions":[{"id":"https://openalex.org/I4210123571","display_name":"Huawei Technologies (France)","ror":"https://ror.org/02rbzf697","country_code":"FR","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210123571"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Carlo Condo","raw_affiliation_strings":["Mathematical and Algorithmic Sciences Lab, Huawei Technologies Co. Ltd, Paris, France"],"raw_orcid":"https://orcid.org/0000-0002-3050-036X","affiliations":[{"raw_affiliation_string":"Mathematical and Algorithmic Sciences Lab, Huawei Technologies Co. Ltd, Paris, France","institution_ids":["https://openalex.org/I4210123571"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091600002","display_name":"Warren J. Gross","orcid":"https://orcid.org/0000-0002-6226-6037"},"institutions":[{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Warren J. Gross","raw_affiliation_strings":["Electrical and Computer Engineering Department, McGill University, Montreal, Canada"],"raw_orcid":"https://orcid.org/0000-0002-6226-6037","affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering Department, McGill University, Montreal, Canada","institution_ids":["https://openalex.org/I5023651"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.847,"has_fulltext":false,"cited_by_count":56,"citation_normalized_percentile":{"value":0.92936434,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":"69","issue":"1","first_page":"138","last_page":"152"},"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":0.9991000294685364,"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/T12702","display_name":"Brain Tumor Detection and Classification","score":0.9972000122070312,"subfield":{"id":"https://openalex.org/subfields/2808","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8676259517669678},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6700021028518677},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.6452467441558838},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.5613225698471069},{"id":"https://openalex.org/keywords/edge-device","display_name":"Edge device","score":0.5228115320205688},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.5133804082870483},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.4944760799407959},{"id":"https://openalex.org/keywords/dataflow","display_name":"Dataflow","score":0.4812707304954529},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.43074682354927063},{"id":"https://openalex.org/keywords/efficient-energy-use","display_name":"Efficient energy use","score":0.42120814323425293},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.3755718469619751},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.22814053297042847},{"id":"https://openalex.org/keywords/wireless","display_name":"Wireless","score":0.1728781759738922},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.14279082417488098}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8676259517669678},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6700021028518677},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.6452467441558838},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.5613225698471069},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.5228115320205688},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.5133804082870483},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.4944760799407959},{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.4812707304954529},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.43074682354927063},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.42120814323425293},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.3755718469619751},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.22814053297042847},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.1728781759738922},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.14279082417488098},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","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},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tc.2019.2941875","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tc.2019.2941875","pdf_url":null,"source":{"id":"https://openalex.org/S157670870","display_name":"IEEE Transactions on Computers","issn_l":"0018-9340","issn":["0018-9340","1557-9956","2326-3814"],"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 Computers","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W1963882359","https://openalex.org/W1999085092","https://openalex.org/W2002555321","https://openalex.org/W2013281636","https://openalex.org/W2048266589","https://openalex.org/W2067523571","https://openalex.org/W2080146741","https://openalex.org/W2112796928","https://openalex.org/W2117539524","https://openalex.org/W2146369740","https://openalex.org/W2147800946","https://openalex.org/W2152567198","https://openalex.org/W2152839228","https://openalex.org/W2155893237","https://openalex.org/W2160280813","https://openalex.org/W2163605009","https://openalex.org/W2194775991","https://openalex.org/W2279098554","https://openalex.org/W2285660444","https://openalex.org/W2289252105","https://openalex.org/W2431931973","https://openalex.org/W2442974303","https://openalex.org/W2516141709","https://openalex.org/W2522548197","https://openalex.org/W2565851976","https://openalex.org/W2565960208","https://openalex.org/W2591982329","https://openalex.org/W2593564159","https://openalex.org/W2594492285","https://openalex.org/W2594836184","https://openalex.org/W2606722458","https://openalex.org/W2612445135","https://openalex.org/W2625457103","https://openalex.org/W2766143712","https://openalex.org/W2767864757","https://openalex.org/W2769815320","https://openalex.org/W2919115771","https://openalex.org/W3024621361","https://openalex.org/W3101558675","https://openalex.org/W4240168186","https://openalex.org/W4297775537","https://openalex.org/W6637373629","https://openalex.org/W6684191040","https://openalex.org/W6695314431","https://openalex.org/W6737664043"],"related_works":["https://openalex.org/W3033233036","https://openalex.org/W3013241373","https://openalex.org/W3176282186","https://openalex.org/W2973622361","https://openalex.org/W4387489555","https://openalex.org/W3185576471","https://openalex.org/W4288024917","https://openalex.org/W4293053895","https://openalex.org/W2983364019","https://openalex.org/W2998183476"],"abstract_inverted_index":{"Convolutional":[0],"neural":[1],"networks":[2],"(CNNs)":[3],"are":[4],"a":[5,81,84,105,109,138,152,166,201,210],"vital":[6],"approach":[7],"in":[8,23,266],"machine":[9],"learning.":[10],"However,":[11,61],"their":[12,116,124],"high":[13,68,72],"complexity":[14],"and":[15,67,135,144,175,186,233,288,292],"energy":[16,78,295],"consumption":[17],"make":[18],"them":[19],"challenging":[20],"to":[21,38,58,76,128,206,254,274,285],"embed":[22],"mobile":[24],"applications":[25],"at":[26],"the":[27,40,170,192,222,226,229,234,245,249,258,275],"edge":[28,44,98,194],"requiring":[29],"real-time":[30,41],"processes":[31],"such":[32,131],"as":[33,132,137],"smart":[34],"phones.":[35],"In":[36,147],"order":[37],"meet":[39],"constraint":[42],"of":[43,65,87,108,140,189,204,212,248,261],"devices,":[45],"recently":[46],"proposed":[47],"custom":[48,95],"hardware":[49],"CNN":[50],"accelerators":[51,96],"have":[52],"exploited":[53],"parallel":[54],"processing":[55],"elements":[56],"(PEs)":[57],"increase":[59],"throughput.":[60],"this":[62,148],"straightforward":[63],"parallelization":[64],"PEs":[66,88],"memory":[69],"bandwidth":[70],"require":[71],"data":[73],"movement,":[74],"leading":[75],"large":[77],"consumption.":[79],"As":[80],"result,":[82],"only":[83],"certain":[85],"number":[86],"can":[89,242,280],"be":[90],"instantiated":[91],"when":[92,126],"designing":[93],"bandwidth-limited":[94,102,193],"targeting":[97,191],"devices.":[99],"While":[100],"most":[101,276],"designs":[103],"claim":[104],"peak":[106,176,235],"performance":[107,119,202,223,232,246],"few":[110],"hundred":[111],"giga":[112],"operations":[113],"per":[114],"second,":[115],"average":[117,174,230],"runtime":[118,231],"is":[120,225,289],"substantially":[121],"lower":[122],"than":[123],"roofline":[125],"applied":[127],"state-of-the-art":[129,213,250],"CNNs":[130,214,251],"AlexNet,":[133],"VGGNet":[134],"ResNet,":[136],"result":[139],"low":[141],"resource":[142],"utilization":[143],"arithmetic":[145,181],"intensity.":[146],"work,":[149],"we":[150],"propose":[151],"zero-activation-skipping":[153],"convolutional":[154],"accelerator":[155],"(ZASCA)":[156],"that":[157,168],"avoids":[158],"noncontributory":[159],"multiplications":[160],"with":[161,218],"zero-valued":[162],"activations.":[163,262],"ZASCA":[164,199,241,279],"employs":[165],"dataflow":[167],"minimizes":[169],"gap":[171],"between":[172,228,290],"its":[173,180,238],"performances":[177],"while":[178,297],"maximizing":[179],"intensity":[182],"for":[183,215],"both":[184],"sparse":[185],"dense":[187,219],"representations":[188],"activations,":[190],"computing":[195],"scenario.":[196],"More":[197],"precisely,":[198],"achieves":[200],"efficiency":[203,224,247],"up":[205,253],"94":[207],"percent":[208],"over":[209],"set":[211],"image":[216],"classification":[217],"representation":[220],"where":[221],"ratio":[227],"performance.":[236],"Using":[237],"zero-skipping":[239],"feature,":[240],"further":[243],"improve":[244],"by":[252],"1.9\u00d7":[255],"depending":[256],"on":[257],"sparsity":[259],"degree":[260],"The":[263],"implementation":[264],"results":[265],"65-nm":[267],"TSMC":[268],"CMOS":[269],"technology":[270],"show":[271],"that,":[272],"compared":[273],"energy-efficient":[277],"accelerator,":[278],"process":[281],"convolutions":[282],"from":[283],"5.5\u00d7":[284],"17.5\u00d7":[286],"faster,":[287],"2.1\u00d7":[291,299],"4.5\u00d7":[293],"more":[294],"efficient":[296],"occupying":[298],"less":[300],"silicon":[301],"area.":[302]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":13},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":14},{"year":2020,"cited_by_count":6}],"updated_date":"2026-06-19T17:40:00.097472","created_date":"2025-10-10T00:00:00"}