{"id":"https://openalex.org/W4401568769","doi":"https://doi.org/10.23919/date58400.2024.10546720","title":"MX: Enhancing RISC-V's Vector ISA for Ultra-Low Overhead, Energy-Efficient Matrix Multiplication","display_name":"MX: Enhancing RISC-V's Vector ISA for Ultra-Low Overhead, Energy-Efficient Matrix Multiplication","publication_year":2024,"publication_date":"2024-03-25","ids":{"openalex":"https://openalex.org/W4401568769","doi":"https://doi.org/10.23919/date58400.2024.10546720"},"language":"en","primary_location":{"id":"doi:10.23919/date58400.2024.10546720","is_oa":false,"landing_page_url":"https://doi.org/10.23919/date58400.2024.10546720","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 Design, Automation &amp;amp; Test in Europe Conference &amp;amp; Exhibition (DATE)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10546720","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5039942285","display_name":"Matteo Perotti","orcid":"https://orcid.org/0000-0003-2413-8592"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Matteo Perotti","raw_affiliation_strings":["ETH Zurich,Zurich,Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Zurich,Zurich,Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100625410","display_name":"Yichao Zhang","orcid":"https://orcid.org/0009-0008-7508-599X"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Yichao Zhang","raw_affiliation_strings":["ETH Zurich,Zurich,Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Zurich,Zurich,Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003158529","display_name":"Matheus Cavalcante","orcid":"https://orcid.org/0000-0001-9199-1708"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Matheus Cavalcante","raw_affiliation_strings":["ETH Zurich,Zurich,Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Zurich,Zurich,Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114137454","display_name":"Enis Mustafa","orcid":null},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Enis Mustafa","raw_affiliation_strings":["ETH Zurich,Zurich,Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Zurich,Zurich,Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043408422","display_name":"Luca Benini","orcid":"https://orcid.org/0000-0001-8068-3806"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Luca Benini","raw_affiliation_strings":["ETH Zurich,Zurich,Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Zurich,Zurich,Switzerland","institution_ids":["https://openalex.org/I35440088"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I35440088"],"apc_list":null,"apc_paid":null,"fwci":5.0144,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.96576743,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10829","display_name":"Interconnection Networks and Systems","score":0.9878000020980835,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9878000020980835,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10363","display_name":"Low-power high-performance VLSI design","score":0.9682999849319458,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9650999903678894,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.6347244381904602},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5916905403137207},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.5012753009796143},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.4848519563674927},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.47225087881088257},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.1531640589237213},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.06694990396499634}],"concepts":[{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.6347244381904602},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5916905403137207},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.5012753009796143},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.4848519563674927},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.47225087881088257},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.1531640589237213},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.06694990396499634},{"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/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.23919/date58400.2024.10546720","is_oa":false,"landing_page_url":"https://doi.org/10.23919/date58400.2024.10546720","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 Design, Automation &amp;amp; Test in Europe Conference &amp;amp; Exhibition (DATE)","raw_type":"proceedings-article"},{"id":"pmh:oai:cris.unibo.it:11585/1004739","is_oa":true,"landing_page_url":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10546720","pdf_url":null,"source":{"id":"https://openalex.org/S4306402579","display_name":"Archivio istituzionale della ricerca (Alma Mater Studiorum Universit\u00e0 di Bologna)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210117483","host_organization_name":"Istituto di Ematologia di Bologna","host_organization_lineage":["https://openalex.org/I4210117483"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:zenodo.org:15675101","is_oa":true,"landing_page_url":"https://doi.org/10.23919/DATE58400.2024.10546720","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"DATE 2024","raw_type":"info:eu-repo/semantics/conferenceProceedings"}],"best_oa_location":{"id":"pmh:oai:cris.unibo.it:11585/1004739","is_oa":true,"landing_page_url":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10546720","pdf_url":null,"source":{"id":"https://openalex.org/S4306402579","display_name":"Archivio istituzionale della ricerca (Alma Mater Studiorum Universit\u00e0 di Bologna)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210117483","host_organization_name":"Istituto di Ematologia di Bologna","host_organization_lineage":["https://openalex.org/I4210117483"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.8399999737739563,"id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W2038454316","https://openalex.org/W2289252105","https://openalex.org/W2801748224","https://openalex.org/W2971544482","https://openalex.org/W2976670629","https://openalex.org/W3105886168","https://openalex.org/W4224228206","https://openalex.org/W4286563542","https://openalex.org/W4293149165","https://openalex.org/W4307079523","https://openalex.org/W4379115985","https://openalex.org/W4386090486","https://openalex.org/W4387064050"],"related_works":["https://openalex.org/W3099313426","https://openalex.org/W4287593139","https://openalex.org/W752783541","https://openalex.org/W1506547947","https://openalex.org/W2995605830","https://openalex.org/W4206811032","https://openalex.org/W2086123442","https://openalex.org/W1925544630","https://openalex.org/W2596457687","https://openalex.org/W3212757063"],"abstract_inverted_index":{"Dense":[0],"Matrix":[1,69],"Multiplication":[2],"(MatMul)":[3],"is":[4,25],"arguably":[5],"one":[6],"of":[7,57,90],"the":[8,55,78,97,162,175,184,188],"most":[9],"ubiquitous":[10],"compute-intensive":[11],"kernels,":[12],"spanning":[13],"linear":[14],"algebra,":[15],"DSP,":[16],"graphics,":[17],"and":[18,52,62,102,129,140,145,152],"machine":[19],"learning":[20],"applications.":[21],"Thus,":[22],"MatMul":[23,50,86],"optimization":[24],"crucial":[26],"not":[27],"only":[28],"in":[29,34,148,155],"high-performance":[30],"processors":[31],"but":[32],"also":[33],"embedded":[35],"low-power":[36],"platforms.":[37],"Several":[38],"Instruction":[39],"Set":[40],"Architectures":[41],"(ISAs)":[42],"have":[43],"recently":[44],"included":[45],"matrix":[46,59],"extensions":[47],"to":[48,84,105],"improve":[49],"performance":[51,197],"efficiency":[53,165],"at":[54,111],"cost":[56],"added":[58],"register":[60,100],"files":[61],"units.":[63],"In":[64],"this":[65],"paper,":[66],"we":[67],"propose":[68],"eXtension":[70],"(MX),":[71],"a":[72,107,112,120,138,150,156,169,195],"lightweight":[73],"approach":[74],"that":[75],"builds":[76],"upon":[77],"open-source":[79],"RISC-V":[80],"Vector":[81],"(RVV)":[82],"ISA":[83],"boost":[85],"energy":[87,164],"efficiency.":[88],"Instead":[89],"adding":[91],"expensive":[92],"dedicated":[93],"hardware,":[94],"MX":[95,136,160],"uses":[96],"pre-existing":[98],"vector":[99],"file":[101],"functional":[103],"units":[104],"create":[106],"hybrid":[108],"vector/matrix":[109],"engine":[110],"negligible":[113],"area":[114],"cost$(&lt;":[115],"3\\%)$,":[116],"which":[117],"comes":[118],"from":[119],"compact":[121,139],"near-FPU":[122],"tile":[123],"buffer":[124],"for":[125,168,187],"higher":[126],"data":[127],"reuse,":[128],"no":[130],"clock":[131],"frequency":[132],"overhead.":[133],"We":[134],"implement":[135],"on":[137,183,191],"highly":[141],"energy-optimized":[142],"RVV":[143],"processor":[144],"evaluate":[146],"it":[147],"both":[149],"Dual-":[151],"64-Core":[153,185],"cluster":[154,186],"12-nm":[157],"technology":[158],"node.":[159],"boosts":[161],"Dual-Core's":[163],"by":[166,180],"10%":[167],"double-precision$64\\times":[170],"64\\times":[171],"64$matrix":[172],"multiplication":[173],"with":[174,194],"same":[176,189],"FPU":[177],"utilization$(\\approx":[178],"97\\%)$and":[179],"25":[181],"%":[182],"benchmark":[190],"32-bit":[192],"data,":[193],"56%":[196],"gain.":[198]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":7}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2024-08-15T00:00:00"}
