{"id":"https://openalex.org/W3091512799","doi":"https://doi.org/10.1109/iscas45731.2020.9180403","title":"A Systolic Dataflow Based Accelerator for CNNs","display_name":"A Systolic Dataflow Based Accelerator for CNNs","publication_year":2020,"publication_date":"2020-09-29","ids":{"openalex":"https://openalex.org/W3091512799","doi":"https://doi.org/10.1109/iscas45731.2020.9180403","mag":"3091512799"},"language":"en","primary_location":{"id":"doi:10.1109/iscas45731.2020.9180403","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscas45731.2020.9180403","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 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/A5062490642","display_name":"Saptarsi Das","orcid":null},"institutions":[{"id":"https://openalex.org/I4210139030","display_name":"Samsung (India)","ror":"https://ror.org/04cpx2569","country_code":"IN","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210139030"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Saptarsi Das","raw_affiliation_strings":["SAIT, Samsung R&D Institute India-Bangalore, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SAIT, Samsung R&D Institute India-Bangalore, India","institution_ids":["https://openalex.org/I4210139030"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100605963","display_name":"Arnab Roy","orcid":"https://orcid.org/0000-0002-3284-7076"},"institutions":[{"id":"https://openalex.org/I4210139030","display_name":"Samsung (India)","ror":"https://ror.org/04cpx2569","country_code":"IN","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210139030"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Arnab Roy","raw_affiliation_strings":["SAIT, Samsung R&D Institute India-Bangalore, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SAIT, Samsung R&D Institute India-Bangalore, India","institution_ids":["https://openalex.org/I4210139030"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072829097","display_name":"Kiran Kolar Chandrasekharan","orcid":"https://orcid.org/0000-0002-0741-6696"},"institutions":[{"id":"https://openalex.org/I4210139030","display_name":"Samsung (India)","ror":"https://ror.org/04cpx2569","country_code":"IN","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210139030"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Kiran Kolar Chandrasekharan","raw_affiliation_strings":["SAIT, Samsung R&D Institute India-Bangalore, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SAIT, Samsung R&D Institute India-Bangalore, India","institution_ids":["https://openalex.org/I4210139030"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017473447","display_name":"Ankur Deshwal","orcid":"https://orcid.org/0000-0002-3046-1292"},"institutions":[{"id":"https://openalex.org/I4210139030","display_name":"Samsung (India)","ror":"https://ror.org/04cpx2569","country_code":"IN","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210139030"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Ankur Deshwal","raw_affiliation_strings":["SAIT, Samsung R&D Institute India-Bangalore, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SAIT, Samsung R&D Institute India-Bangalore, India","institution_ids":["https://openalex.org/I4210139030"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032109382","display_name":"Sehwan Lee","orcid":"https://orcid.org/0000-0001-5504-974X"},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sehwan Lee","raw_affiliation_strings":["SAIT, Samsung Electronics, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SAIT, Samsung Electronics, South Korea","institution_ids":["https://openalex.org/I2250650973"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1747,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.81562138,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"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":0.9994000196456909,"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":0.9994000196456909,"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":0.9965000152587891,"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"}},{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9945999979972839,"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/dataflow","display_name":"Dataflow","score":0.9463545083999634},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.791662335395813},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6589487791061401},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.6154968738555908},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.6079888939857483},{"id":"https://openalex.org/keywords/hardware-acceleration","display_name":"Hardware acceleration","score":0.6072021722793579},{"id":"https://openalex.org/keywords/efficient-energy-use","display_name":"Efficient energy use","score":0.5991081595420837},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5800510048866272},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.5304859280586243},{"id":"https://openalex.org/keywords/systolic-array","display_name":"Systolic array","score":0.527413010597229},{"id":"https://openalex.org/keywords/acceleration","display_name":"Acceleration","score":0.5259984731674194},{"id":"https://openalex.org/keywords/power-budget","display_name":"Power budget","score":0.4695224165916443},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.46166497468948364},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.45511773228645325},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4378885328769684},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.41732946038246155},{"id":"https://openalex.org/keywords/electrical-efficiency","display_name":"Electrical efficiency","score":0.4104742407798767},{"id":"https://openalex.org/keywords/very-large-scale-integration","display_name":"Very-large-scale integration","score":0.39385098218917847},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.3899151384830475},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.36567944288253784},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.23551735281944275},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.19169428944587708},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.1641812026500702},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.14965477585792542},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.09691733121871948},{"id":"https://openalex.org/keywords/wireless","display_name":"Wireless","score":0.08920913934707642},{"id":"https://openalex.org/keywords/power-control","display_name":"Power control","score":0.08504325151443481},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07238462567329407}],"concepts":[{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.9463545083999634},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.791662335395813},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6589487791061401},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.6154968738555908},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.6079888939857483},{"id":"https://openalex.org/C13164978","wikidata":"https://www.wikidata.org/wiki/Q600158","display_name":"Hardware acceleration","level":3,"score":0.6072021722793579},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.5991081595420837},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5800510048866272},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.5304859280586243},{"id":"https://openalex.org/C150741067","wikidata":"https://www.wikidata.org/wiki/Q2377218","display_name":"Systolic array","level":3,"score":0.527413010597229},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.5259984731674194},{"id":"https://openalex.org/C149768029","wikidata":"https://www.wikidata.org/wiki/Q1509342","display_name":"Power budget","level":4,"score":0.4695224165916443},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.46166497468948364},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.45511773228645325},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4378885328769684},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.41732946038246155},{"id":"https://openalex.org/C118993495","wikidata":"https://www.wikidata.org/wiki/Q5042828","display_name":"Electrical efficiency","level":3,"score":0.4104742407798767},{"id":"https://openalex.org/C14580979","wikidata":"https://www.wikidata.org/wiki/Q876049","display_name":"Very-large-scale integration","level":2,"score":0.39385098218917847},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.3899151384830475},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.36567944288253784},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23551735281944275},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.19169428944587708},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1641812026500702},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.14965477585792542},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.09691733121871948},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.08920913934707642},{"id":"https://openalex.org/C56685638","wikidata":"https://www.wikidata.org/wiki/Q2300474","display_name":"Power control","level":3,"score":0.08504325151443481},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07238462567329407},{"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/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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscas45731.2020.9180403","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscas45731.2020.9180403","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 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":0.9100000262260437,"display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2000967104","https://openalex.org/W2048266589","https://openalex.org/W2067523571","https://openalex.org/W2152839228","https://openalex.org/W2172119162","https://openalex.org/W2285660444","https://openalex.org/W2289252105","https://openalex.org/W2516141709","https://openalex.org/W2606722458","https://openalex.org/W2612076670","https://openalex.org/W2625954420","https://openalex.org/W2750173518","https://openalex.org/W2797388134","https://openalex.org/W2802238174","https://openalex.org/W2908078360","https://openalex.org/W2921967969","https://openalex.org/W2950656546","https://openalex.org/W4212788319","https://openalex.org/W4234863022","https://openalex.org/W4247470470","https://openalex.org/W6685311839"],"related_works":["https://openalex.org/W2998381397","https://openalex.org/W4236419692","https://openalex.org/W3167919718","https://openalex.org/W4225271228","https://openalex.org/W1484403103","https://openalex.org/W2568698427","https://openalex.org/W2365647065","https://openalex.org/W3140218589","https://openalex.org/W2538397358","https://openalex.org/W3011055022"],"abstract_inverted_index":{"Modern":[0],"Artificial":[1],"Intelligence":[2],"(AI)":[3],"systems":[4],"deploy":[5],"Convolution":[6],"Neural":[7],"Networks":[8],"(CNN)":[9],"as":[10,57,59],"they":[11],"offer":[12],"very":[13],"high":[14],"accuracy.":[15],"Computational":[16],"complexity":[17],"of":[18,53,66,77,87,89,100,126,134,142],"CNNs":[19],"necessitates":[20],"hardware":[21],"acceleration,":[22],"especially":[23],"in":[24],"mobile":[25],"phones":[26],"and":[27,36],"other":[28],"hand":[29],"held":[30],"devices":[31],"due":[32,116],"to":[33,112,117,136],"stringent":[34],"power":[35,81,107,114,130],"area":[37],"budget.":[38],"In":[39],"this":[40],"paper,":[41],"we":[42],"propose":[43],"a":[44,64,85],"systolic":[45],"dataflow":[46],"based":[47],"accelerator":[48,69,102,123],"architecture":[49],"with":[50,106],"the":[51,90,98,101,127],"aim":[52],"improving":[54],"energy":[55],"efficiency":[56,82,131],"well":[58],"scalability.":[60],"We":[61,94],"demonstrate":[62],"that":[63,97],"prototype":[65],"our":[67],"proposed":[68,122],"comprising":[70],"4096":[71],"Multiply-Accumulate":[72],"(MAC)":[73],"units":[74],"is":[75,110],"capable":[76],"achieving":[78],"8.89-9.54":[79],"TOPs/W":[80],"when":[83],"executing":[84,139],"number":[86],"state":[88,125],"art":[91,128],"CNN":[92],"models.":[93],"also":[95],"observe":[96],"throughput":[99],"scales":[103],"almost":[104],"linearly":[105],"dissipated.":[108],"This":[109],"attributed":[111],"low":[113],"consumption":[115],"minimal":[118],"non-compute":[119],"overhead.":[120],"Our":[121],"outperforms":[124],"accelerators":[129],"by":[132],"factors":[133],"2.6":[135],"3.8\u00d7":[137],"while":[138],"various":[140],"layers":[141],"Inception":[143],"V3":[144],"model.":[145]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}