{"id":"https://openalex.org/W4365131896","doi":"https://doi.org/10.1109/apccas55924.2022.10090307","title":"SME: A Systolic Multiply-accumulate Engine for MLP-based Neural Network","display_name":"SME: A Systolic Multiply-accumulate Engine for MLP-based Neural Network","publication_year":2022,"publication_date":"2022-11-11","ids":{"openalex":"https://openalex.org/W4365131896","doi":"https://doi.org/10.1109/apccas55924.2022.10090307"},"language":"en","primary_location":{"id":"doi:10.1109/apccas55924.2022.10090307","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/apccas55924.2022.10090307","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE Asia Pacific Conference on Circuits and Systems (APCCAS)","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/A5018248281","display_name":"Haochuan Wan","orcid":"https://orcid.org/0000-0002-0996-6325"},"institutions":[{"id":"https://openalex.org/I30809798","display_name":"ShanghaiTech University","ror":"https://ror.org/030bhh786","country_code":"CN","type":"education","lineage":["https://openalex.org/I30809798"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haochuan Wan","raw_affiliation_strings":["School of Information Science and Technology, ShanghaiTech University,Shanghai,China","School of Information Science and Technology, ShanghaiTech University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, ShanghaiTech University,Shanghai,China","institution_ids":["https://openalex.org/I30809798"]},{"raw_affiliation_string":"School of Information Science and Technology, ShanghaiTech University, Shanghai, China","institution_ids":["https://openalex.org/I30809798"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030149715","display_name":"Chaolin Rao","orcid":"https://orcid.org/0000-0003-2172-5361"},"institutions":[{"id":"https://openalex.org/I30809798","display_name":"ShanghaiTech University","ror":"https://ror.org/030bhh786","country_code":"CN","type":"education","lineage":["https://openalex.org/I30809798"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chaolin Rao","raw_affiliation_strings":["School of Information Science and Technology, ShanghaiTech University,Shanghai,China","School of Information Science and Technology, ShanghaiTech University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, ShanghaiTech University,Shanghai,China","institution_ids":["https://openalex.org/I30809798"]},{"raw_affiliation_string":"School of Information Science and Technology, ShanghaiTech University, Shanghai, China","institution_ids":["https://openalex.org/I30809798"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101221476","display_name":"Yueyang Zheng","orcid":null},"institutions":[{"id":"https://openalex.org/I30809798","display_name":"ShanghaiTech University","ror":"https://ror.org/030bhh786","country_code":"CN","type":"education","lineage":["https://openalex.org/I30809798"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yueyang Zheng","raw_affiliation_strings":["School of Information Science and Technology, ShanghaiTech University,Shanghai,China","School of Information Science and Technology, ShanghaiTech University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, ShanghaiTech University,Shanghai,China","institution_ids":["https://openalex.org/I30809798"]},{"raw_affiliation_string":"School of Information Science and Technology, ShanghaiTech University, Shanghai, China","institution_ids":["https://openalex.org/I30809798"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081772659","display_name":"Pingqiang Zhou","orcid":"https://orcid.org/0000-0001-9515-9302"},"institutions":[{"id":"https://openalex.org/I30809798","display_name":"ShanghaiTech University","ror":"https://ror.org/030bhh786","country_code":"CN","type":"education","lineage":["https://openalex.org/I30809798"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pingqiang Zhou","raw_affiliation_strings":["School of Information Science and Technology, ShanghaiTech University,Shanghai,China","School of Information Science and Technology, ShanghaiTech University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, ShanghaiTech University,Shanghai,China","institution_ids":["https://openalex.org/I30809798"]},{"raw_affiliation_string":"School of Information Science and Technology, ShanghaiTech University, Shanghai, China","institution_ids":["https://openalex.org/I30809798"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063714836","display_name":"Xin Lou","orcid":"https://orcid.org/0000-0002-8499-5038"},"institutions":[{"id":"https://openalex.org/I30809798","display_name":"ShanghaiTech University","ror":"https://ror.org/030bhh786","country_code":"CN","type":"education","lineage":["https://openalex.org/I30809798"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Lou","raw_affiliation_strings":["School of Information Science and Technology, ShanghaiTech University,Shanghai,China","School of Information Science and Technology, ShanghaiTech University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, ShanghaiTech University,Shanghai,China","institution_ids":["https://openalex.org/I30809798"]},{"raw_affiliation_string":"School of Information Science and Technology, ShanghaiTech University, Shanghai, China","institution_ids":["https://openalex.org/I30809798"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I30809798"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16737126,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"65","issue":null,"first_page":"270","last_page":"274"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9943000078201294,"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":0.9943000078201294,"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/T10320","display_name":"Neural Networks and Applications","score":0.9905999898910522,"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.9858999848365784,"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/artificial-neural-network","display_name":"Artificial neural network","score":0.6963609457015991},{"id":"https://openalex.org/keywords/dataflow","display_name":"Dataflow","score":0.6498822569847107},{"id":"https://openalex.org/keywords/activation-function","display_name":"Activation function","score":0.6251236796379089},{"id":"https://openalex.org/keywords/very-large-scale-integration","display_name":"Very-large-scale integration","score":0.6007479429244995},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5965545773506165},{"id":"https://openalex.org/keywords/cmos","display_name":"CMOS","score":0.543666422367096},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.45216405391693115},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4234585165977478},{"id":"https://openalex.org/keywords/multilayer-perceptron","display_name":"Multilayer perceptron","score":0.4112819731235504},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3384125232696533},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3125316798686981},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.21094658970832825},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.19177782535552979},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.17074131965637207},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.10881844162940979}],"concepts":[{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6963609457015991},{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.6498822569847107},{"id":"https://openalex.org/C38365724","wikidata":"https://www.wikidata.org/wiki/Q4677469","display_name":"Activation function","level":3,"score":0.6251236796379089},{"id":"https://openalex.org/C14580979","wikidata":"https://www.wikidata.org/wiki/Q876049","display_name":"Very-large-scale integration","level":2,"score":0.6007479429244995},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5965545773506165},{"id":"https://openalex.org/C46362747","wikidata":"https://www.wikidata.org/wiki/Q173431","display_name":"CMOS","level":2,"score":0.543666422367096},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.45216405391693115},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4234585165977478},{"id":"https://openalex.org/C179717631","wikidata":"https://www.wikidata.org/wiki/Q2991667","display_name":"Multilayer perceptron","level":3,"score":0.4112819731235504},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3384125232696533},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3125316798686981},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.21094658970832825},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.19177782535552979},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.17074131965637207},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.10881844162940979},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apccas55924.2022.10090307","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/apccas55924.2022.10090307","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE Asia Pacific Conference on Circuits and Systems (APCCAS)","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":19,"referenced_works":["https://openalex.org/W2067132795","https://openalex.org/W2285660444","https://openalex.org/W2289252105","https://openalex.org/W2540279855","https://openalex.org/W2606722458","https://openalex.org/W2963627347","https://openalex.org/W3043139608","https://openalex.org/W3092203888","https://openalex.org/W3097528158","https://openalex.org/W3136656704","https://openalex.org/W3159198872","https://openalex.org/W3184957317","https://openalex.org/W3202371506","https://openalex.org/W4200150166","https://openalex.org/W4221151978","https://openalex.org/W4236868170","https://openalex.org/W4304140727","https://openalex.org/W4311806033","https://openalex.org/W6781421651"],"related_works":["https://openalex.org/W2053362666","https://openalex.org/W2157934879","https://openalex.org/W3122190249","https://openalex.org/W2140019974","https://openalex.org/W4296307178","https://openalex.org/W4316021339","https://openalex.org/W3128026563","https://openalex.org/W115603095","https://openalex.org/W4387528827","https://openalex.org/W4205825681"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"propose":[4],"an":[5,13],"output":[6],"stationary":[7],"systolic":[8],"multiply-accumulate":[9],"engine":[10],"(SME)":[11],"with":[12],"optimized":[14],"dataflow":[15],"for":[16,74,89],"multilayer":[17],"perceptron":[18],"(MLP)":[19],"computation":[20],"in":[21,54,71],"the":[22,35,42,48,55,72,104],"state-of-the-art":[23],"Neural":[24],"Radiance":[25],"Field":[26],"(NeRF)":[27],"algorithms.":[28],"We":[29,59],"also":[30],"analyze":[31],"activation":[32,43,49,65],"patterns":[33],"of":[34,64],"NeRF":[36],"algorithm":[37],"which":[38,84],"uses":[39],"ReLU":[40],"as":[41],"function,":[44],"and":[45,111,118],"find":[46],"that":[47],"can":[50],"be":[51],"sparse,":[52],"especially":[53],"last":[56],"several":[57],"layers.":[58],"therefore":[60],"further":[61],"take":[62],"advantage":[63],"sparsity":[66],"by":[67],"gating":[68],"corresponding":[69],"multiplications":[70],"SME":[73,79,106],"power":[75],"saving.":[76],"The":[77],"proposed":[78,105],"is":[80,85],"implemented":[81],"using":[82],"SpinalHDL,":[83],"translated":[86],"to":[87],"VerilogHDL":[88],"VLSI":[90],"implementation":[91],"based":[92],"on":[93],"40nm":[94],"CMOS":[95],"technology.":[96],"Evaluation":[97],"results":[98],"show":[99],"that,":[100],"working":[101],"at":[102],"400MHz,":[103],"occupies":[107],"31.371mm<sup>2</sup>":[108],"circuit":[109],"area,":[110],"consumes":[112],"873.7mW":[113],"power,":[114],"translating":[115],"12,708.10":[116],"ksamples/J":[117],"360.06":[119],"ksamples/s/mm<sup>2</sup>.":[120]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}