{"id":"https://openalex.org/W4391462013","doi":"https://doi.org/10.1109/iscas58744.2024.10558028","title":"A Scalable RISC-V Vector Processor Enabling Efficient Multi-Precision DNN Inference","display_name":"A Scalable RISC-V Vector Processor Enabling Efficient Multi-Precision DNN Inference","publication_year":2024,"publication_date":"2024-05-19","ids":{"openalex":"https://openalex.org/W4391462013","doi":"https://doi.org/10.1109/iscas58744.2024.10558028"},"language":"en","primary_location":{"id":"doi:10.1109/iscas58744.2024.10558028","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscas58744.2024.10558028","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Symposium on Circuits and Systems (ISCAS)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2401.16872","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5053683099","display_name":"Chuanning Wang","orcid":"https://orcid.org/0000-0002-0803-0015"},"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":"Chuanning Wang","raw_affiliation_strings":["Nanjing University,School of Electronic Science and Engineering,Nanjing,China"],"affiliations":[{"raw_affiliation_string":"Nanjing University,School of Electronic Science and Engineering,Nanjing,China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103213382","display_name":"Chao Fang","orcid":"https://orcid.org/0000-0003-4967-0411"},"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":"Chao Fang","raw_affiliation_strings":["Nanjing University,School of Electronic Science and Engineering,Nanjing,China"],"affiliations":[{"raw_affiliation_string":"Nanjing University,School of Electronic Science and Engineering,Nanjing,China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011680564","display_name":"Xiao Wu","orcid":"https://orcid.org/0000-0002-8322-8558"},"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":"Xiao Wu","raw_affiliation_strings":["Nanjing University,School of Electronic Science and Engineering,Nanjing,China"],"affiliations":[{"raw_affiliation_string":"Nanjing University,School of Electronic Science and Engineering,Nanjing,China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100697000","display_name":"Zhongfeng Wang","orcid":"https://orcid.org/0000-0003-0402-7334"},"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":"Zhongfeng Wang","raw_affiliation_strings":["Nanjing University,School of Electronic Science and Engineering,Nanjing,China"],"affiliations":[{"raw_affiliation_string":"Nanjing University,School of Electronic Science and Engineering,Nanjing,China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101534216","display_name":"Jun Lin","orcid":"https://orcid.org/0000-0003-2291-309X"},"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":"Jun Lin","raw_affiliation_strings":["Nanjing University,School of Electronic Science and Engineering,Nanjing,China"],"affiliations":[{"raw_affiliation_string":"Nanjing University,School of Electronic Science and Engineering,Nanjing,China","institution_ids":["https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5053683099"],"corresponding_institution_ids":["https://openalex.org/I881766915"],"apc_list":null,"apc_paid":null,"fwci":2.856,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.90269793,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"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/T13717","display_name":"Advanced Algorithms and Applications","score":0.8989999890327454,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T13717","display_name":"Advanced Algorithms and Applications","score":0.8989999890327454,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/T10876","display_name":"Fault Detection and Control Systems","score":0.892799973487854,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/T10320","display_name":"Neural Networks and Applications","score":0.8877999782562256,"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":0.7019684910774231},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6482906341552734},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6266165375709534},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.4214795231819153},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.39385098218917847},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3775187134742737},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.12868043780326843}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7019684910774231},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6482906341552734},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6266165375709534},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.4214795231819153},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.39385098218917847},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3775187134742737},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.12868043780326843}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/iscas58744.2024.10558028","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscas58744.2024.10558028","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Symposium on Circuits and Systems (ISCAS)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2401.16872","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2401.16872","pdf_url":"https://arxiv.org/pdf/2401.16872","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2401.16872","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2401.16872","pdf_url":"https://arxiv.org/pdf/2401.16872","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.8999999761581421,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[{"id":"https://openalex.org/G192642426","display_name":null,"funder_award_id":"2174084","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2250357272","display_name":null,"funder_award_id":"62174084","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2635439592","display_name":null,"funder_award_id":"2022YFB4400604","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5354445887","display_name":null,"funder_award_id":"62341408","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320324852","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4391462013.pdf"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W2097117768","https://openalex.org/W2194775991","https://openalex.org/W2417429787","https://openalex.org/W2799238091","https://openalex.org/W2936567838","https://openalex.org/W2994193159","https://openalex.org/W3158912502","https://openalex.org/W3203242999","https://openalex.org/W4205884968","https://openalex.org/W4245873651","https://openalex.org/W4280493494","https://openalex.org/W4307079523","https://openalex.org/W4308083752","https://openalex.org/W4312298069","https://openalex.org/W4327522190","https://openalex.org/W4372265769","https://openalex.org/W4383220308","https://openalex.org/W4384947576","https://openalex.org/W4385624933","https://openalex.org/W4393141038","https://openalex.org/W6695314431","https://openalex.org/W6731058201","https://openalex.org/W6848789543","https://openalex.org/W6966527820"],"related_works":["https://openalex.org/W2389214306","https://openalex.org/W2965083567","https://openalex.org/W4235240664","https://openalex.org/W1838576100","https://openalex.org/W2757182831","https://openalex.org/W2095886385","https://openalex.org/W2089704382","https://openalex.org/W1983399550","https://openalex.org/W97075385","https://openalex.org/W121182129"],"abstract_inverted_index":{"RISC-V":[0,30,57],"processors":[1],"encounter":[2],"substantial":[3],"challenges":[4],"in":[5,130],"deploying":[6],"multi-precision":[7,41,82,104,193],"deep":[8],"neural":[9],"networks":[10],"(DNNs)":[11],"due":[12],"to":[13,38,76,92,117,162],"their":[14],"restricted":[15],"precision":[16,72,156,183],"support,":[17],"constrained":[18],"throughput,":[19],"and":[20,51,97,112,122,147,177,181],"suboptimal":[21],"dataflow":[22,52,105],"design.":[23],"To":[24],"tackle":[25],"these":[26],"challenges,":[27],"a":[28,80,102,141],"scalable":[29,90],"vector":[31,166],"(RVV)":[32],"processor,":[33],"namely":[34],"SPEED,":[35],"is":[36,86,115],"proposed":[37,60,116],"enable":[39],"efficient":[40,192],"DNN":[42,194],"inference":[43],"by":[44],"innovations":[45],"from":[46,74],"customized":[47,56],"instructions,":[48],"hardware":[49],"architecture,":[50],"mapping.":[53],"Firstly,":[54],"dedicated":[55],"instructions":[58],"are":[59],"based":[61],"on":[62],"RVV":[63],"extensions,":[64],"providing":[65],"SPEED":[66,129,139,169],"with":[67,108],"fine-grained":[68],"control":[69],"over":[70],"processing":[71,95],"ranging":[73],"4":[75],"16":[77],"bits.":[78],"Secondly,":[79],"parameterized":[81],"systolic":[83],"array":[84],"unit":[85],"incorporated":[87],"within":[88],"the":[89,163],"module":[91],"enhance":[93],"parallel":[94],"capability":[96],"data":[98,113,120],"reuse":[99],"opportunities.":[100],"Finally,":[101],"mixed":[103],"strategy,":[106],"compatible":[107],"different":[109],"convolution":[110],"kernels":[111],"precision,":[114],"effectively":[118],"improve":[119],"utilization":[121],"computational":[123],"efficiency.":[124],"We":[125],"perform":[126],"synthesis":[127],"of":[128,144,151,175],"TSMC":[131],"28nm":[132],"technology.":[133],"The":[134],"experimental":[135],"results":[136],"demonstrate":[137],"that":[138],"achieves":[140],"peak":[142],"throughput":[143],"287.41":[145],"GOPS":[146],"an":[148,171],"energy":[149],"efficiency":[150,173],"1335.79":[152],"GOPS/W":[153],"at":[154],"4-bit":[155],"condition,":[157],"respectively.":[158],"Moreover,":[159],"when":[160],"compared":[161],"pioneer":[164],"open-source":[165],"processor":[167],"Ara,":[168],"provides":[170],"area":[172],"improvement":[174],"2.04\u00d7":[176],"1.63\u00d7":[178],"under":[179],"16-bit":[180],"8-bit":[182],"conditions,":[184],"respectively,":[185],"which":[186],"shows":[187],"SPEED\u2019s":[188],"significant":[189],"potential":[190],"for":[191],"inference.":[195]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":2}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}