{"id":"https://openalex.org/W4403122884","doi":"https://doi.org/10.1109/tvlsi.2024.3466224","title":"SPEED: A Scalable RISC-V Vector Processor Enabling Efficient Multiprecision DNN Inference","display_name":"SPEED: A Scalable RISC-V Vector Processor Enabling Efficient Multiprecision DNN Inference","publication_year":2024,"publication_date":"2024-10-04","ids":{"openalex":"https://openalex.org/W4403122884","doi":"https://doi.org/10.1109/tvlsi.2024.3466224"},"language":"en","primary_location":{"id":"doi:10.1109/tvlsi.2024.3466224","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tvlsi.2024.3466224","pdf_url":null,"source":{"id":"https://openalex.org/S37538908","display_name":"IEEE Transactions on Very Large Scale Integration (VLSI) Systems","issn_l":"1063-8210","issn":["1063-8210","1557-9999"],"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 Very Large Scale Integration (VLSI) Systems","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2409.14017","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Chuanning Wang","orcid":"https://orcid.org/0009-0000-2744-8882"},"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":"Chuanning Wang","raw_affiliation_strings":["School of Electronic Science and Engineering, Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0000-2744-8882","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":null,"display_name":"Chao Fang","orcid":"https://orcid.org/0000-0003-3430-1189"},"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":["School of Electronic Science and Engineering, Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0003-3430-1189","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/A5091293910","display_name":"Xiao Wu","orcid":"https://orcid.org/0000-0001-8306-6889"},"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":["School of Electronic Science and Engineering, Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0001-8306-6889","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":null,"display_name":"Zhongfeng Wang","orcid":"https://orcid.org/0000-0002-7227-4786"},"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":["School of Electronic Science and Engineering, Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-7227-4786","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/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":["School of Electronic Science and Engineering and the Interdisciplinary Research Center for Future Intelligent Chips (Chip-X), Nanjing University, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic Science and Engineering and the Interdisciplinary Research Center for Future Intelligent Chips (Chip-X), Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I881766915"],"apc_list":null,"apc_paid":null,"fwci":1.6663,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":{"value":0.84173853,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"33","issue":"1","first_page":"207","last_page":"220"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12702","display_name":"Brain Tumor Detection and Classification","score":0.9326000213623047,"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"}},"topics":[{"id":"https://openalex.org/T12702","display_name":"Brain Tumor Detection and Classification","score":0.9326000213623047,"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"}},{"id":"https://openalex.org/T11324","display_name":"Spectroscopy Techniques in Biomedical and Chemical Research","score":0.9017999768257141,"subfield":{"id":"https://openalex.org/subfields/1304","display_name":"Biophysics"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6761913299560547},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6176677942276001},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5580710768699646},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5004262924194336},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.37976446747779846},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.240579754114151},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.19112545251846313}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6761913299560547},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6176677942276001},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5580710768699646},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5004262924194336},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.37976446747779846},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.240579754114151},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.19112545251846313}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tvlsi.2024.3466224","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tvlsi.2024.3466224","pdf_url":null,"source":{"id":"https://openalex.org/S37538908","display_name":"IEEE Transactions on Very Large Scale Integration (VLSI) Systems","issn_l":"1063-8210","issn":["1063-8210","1557-9999"],"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 Very Large Scale Integration (VLSI) Systems","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2409.14017","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2409.14017","pdf_url":"https://arxiv.org/pdf/2409.14017","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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:2409.14017","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2409.14017","pdf_url":"https://arxiv.org/pdf/2409.14017","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.4699999988079071}],"awards":[{"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"},{"id":"https://openalex.org/G6422954184","display_name":null,"funder_award_id":"2022YFB4400600","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G8081350091","display_name":null,"funder_award_id":"2022YFB4400600","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/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4403122884.pdf","grobid_xml":"https://content.openalex.org/works/W4403122884.grobid-xml"},"referenced_works_count":48,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2417429787","https://openalex.org/W2540279855","https://openalex.org/W2799238091","https://openalex.org/W2889339831","https://openalex.org/W2891335318","https://openalex.org/W2895531329","https://openalex.org/W2906663849","https://openalex.org/W2950656546","https://openalex.org/W2963163009","https://openalex.org/W2963255460","https://openalex.org/W2967733054","https://openalex.org/W2982479999","https://openalex.org/W2994193159","https://openalex.org/W2998342322","https://openalex.org/W3121523901","https://openalex.org/W3134759918","https://openalex.org/W3156145546","https://openalex.org/W3157114665","https://openalex.org/W3160243752","https://openalex.org/W3203003533","https://openalex.org/W3203242999","https://openalex.org/W3214740560","https://openalex.org/W4205884968","https://openalex.org/W4212886211","https://openalex.org/W4221152838","https://openalex.org/W4230989867","https://openalex.org/W4238341497","https://openalex.org/W4246193833","https://openalex.org/W4280493494","https://openalex.org/W4291653336","https://openalex.org/W4307079523","https://openalex.org/W4308083752","https://openalex.org/W4312298069","https://openalex.org/W4312569226","https://openalex.org/W4327522190","https://openalex.org/W4372265769","https://openalex.org/W4383220308","https://openalex.org/W4384947576","https://openalex.org/W4385245566","https://openalex.org/W4385624933","https://openalex.org/W4388505295","https://openalex.org/W4393141038","https://openalex.org/W4395680644","https://openalex.org/W6731058201","https://openalex.org/W6763701032","https://openalex.org/W6778883912","https://openalex.org/W6796494063"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2389214306","https://openalex.org/W4396696052","https://openalex.org/W4401278057"],"abstract_inverted_index":{"Deploying":[0],"deep":[1],"neural":[2],"networks":[3],"(DNNs)":[4],"on":[5,91,175],"those":[6],"resource-constrained":[7],"edge":[8],"platforms":[9],"is":[10,65,121,152,173],"hindered":[11],"by":[12,134],"their":[13],"substantial":[14],"computation":[15,141],"and":[16,48,79,123,157,191,222],"storage":[17],"demands.":[18],"Quantized":[19],"multiprecision":[20,117],"DNNs":[21],"(MP-DNNs),":[22],"denoted":[23],"as":[24],"MP-DNNs,":[25],"offer":[26],"a":[27,59,115,147,185],"promising":[28],"solution":[29],"for":[30,36,198,232],"these":[31],"limitations":[32],"but":[33],"pose":[34],"challenges":[35,55],"the":[37,54,96,126,140,162,213],"existing":[38],"RISC-V":[39,61,86],"processors":[40],"due":[41],"to":[42,67,94,101,108,129,154,161],"complex":[43],"instructions,":[44,76],"suboptimal":[45],"parallel":[46,131],"processing,":[47],"inefficient":[49],"dataflow":[50,80,150],"mapping.":[51,81],"To":[52],"tackle":[53],"mentioned":[56],"above,":[57],"SPEED,":[58],"scalable":[60,127],"vector":[62],"(RVV)":[63],"processor,":[64],"proposed":[66],"enable":[68],"efficient":[69,233],"MP-DNN":[70,234],"inference,":[71],"incorporating":[72],"innovations":[73],"in":[74],"customized":[75,85],"hardware":[77,112],"architecture,":[78],"First,":[82],"some":[83],"dedicated":[84],"instructions":[87],"are":[88],"introduced":[89],"based":[90],"RVV":[92,210],"extensions":[93],"reduce":[95],"instruction":[97],"complexity,":[98],"allowing":[99],"SPEED":[100,172,183,202],"support":[102],"processing":[103,132],"precision":[104],"ranging":[105],"from":[106],"4-":[107],"16-bit":[109],"with":[110,208,212],"minimized":[111],"overhead.":[113],"Second,":[114],"parameterized":[116],"tensor":[118],"unit":[119],"(MPTU)":[120],"developed":[122],"integrated":[124],"within":[125],"module":[128],"enhance":[130],"capability":[133],"providing":[135],"reconfigurable":[136],"parallelism":[137],"that":[138,182],"matches":[139],"patterns":[142,164],"of":[143,165,171,188,195],"diverse":[144],"MP-DNNs.":[145],"Finally,":[146],"flexible":[148],"mixed":[149],"method":[151],"adopted":[153],"improve":[155],"computational":[156],"energy":[158,193],"efficiency":[159,194,206],"according":[160],"computing":[163],"different":[166],"DNN":[167],"operators.":[168,200],"The":[169],"synthesis":[170],"conducted":[174],"TSMC":[176],"28-nm":[177],"technology.":[178],"Experimental":[179],"results":[180],"show":[181],"achieves":[184],"peak":[186],"throughput":[187],"737.9":[189],"GOPS":[190],"an":[192],"1383.4":[196],"GOPS/W":[197],"4-bit":[199],"Furthermore,":[201],"exhibits":[203],"superior":[204],"area":[205],"compared":[207],"prior":[209],"processors,":[211],"enhancements":[214],"of$5.9\\sim":[215],"26.9\\times":[216],"$and$8.2\\sim":[217],"18.5\\times":[218],"$for":[219],"8-bit":[220],"operator":[221],"best":[223],"integer":[224],"performance,":[225],"respectively,":[226],"which":[227],"highlights":[228],"SPEED\u2019s":[229],"significant":[230],"potential":[231],"inference.":[235]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2024-10-05T00:00:00"}
