{"id":"https://openalex.org/W4394805411","doi":"https://doi.org/10.1109/tc.2024.3388896","title":"Ara2: Exploring Single- and Multi-Core Vector Processing With an Efficient RVV 1.0 Compliant Open-Source Processor","display_name":"Ara2: Exploring Single- and Multi-Core Vector Processing With an Efficient RVV 1.0 Compliant Open-Source Processor","publication_year":2024,"publication_date":"2024-04-15","ids":{"openalex":"https://openalex.org/W4394805411","doi":"https://doi.org/10.1109/tc.2024.3388896"},"language":"en","primary_location":{"id":"doi:10.1109/tc.2024.3388896","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tc.2024.3388896","pdf_url":null,"source":{"id":"https://openalex.org/S157670870","display_name":"IEEE Transactions on Computers","issn_l":"0018-9340","issn":["0018-9340","1557-9956","2326-3814"],"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 Computers","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://cris.unibo.it/bitstream/11585/1004690/3/2311.07493v2.pdf","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":["Integrated Systems Laboratory (IIS), ETH Zurich, Zurich, Switzerland"],"raw_orcid":"https://orcid.org/0000-0003-2413-8592","affiliations":[{"raw_affiliation_string":"Integrated Systems Laboratory (IIS), 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/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matheus Cavalcante","raw_affiliation_strings":["Electrical Engineering Department, Stanford University, California, CA, USA"],"raw_orcid":"https://orcid.org/0000-0001-9199-1708","affiliations":[{"raw_affiliation_string":"Electrical Engineering Department, Stanford University, California, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050957615","display_name":"Renzo Andri","orcid":"https://orcid.org/0000-0002-8776-5158"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Renzo Andri","raw_affiliation_strings":["Huawei Zurich Research Center, Zurich, Switzerland"],"raw_orcid":"https://orcid.org/0000-0002-8776-5158","affiliations":[{"raw_affiliation_string":"Huawei Zurich Research Center, Zurich, Switzerland","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025399641","display_name":"Lukas Cavigelli","orcid":"https://orcid.org/0000-0003-1767-7715"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lukas Cavigelli","raw_affiliation_strings":["Huawei Zurich Research Center, Zurich, Switzerland"],"raw_orcid":"https://orcid.org/0000-0003-1767-7715","affiliations":[{"raw_affiliation_string":"Huawei Zurich Research Center, Zurich, Switzerland","institution_ids":[]}]},{"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"]},{"id":"https://openalex.org/I9360294","display_name":"University of Bologna","ror":"https://ror.org/01111rn36","country_code":"IT","type":"education","lineage":["https://openalex.org/I9360294"]}],"countries":["CH","IT"],"is_corresponding":false,"raw_author_name":"Luca Benini","raw_affiliation_strings":["Integrated Systems Laboratory (IIS), ETH Zurich, Zurich, Switzerland","Department of Electrical, Electronic and Information Engineering (DEI), University of Bologna, Bologna, Italy"],"raw_orcid":"https://orcid.org/0000-0001-8068-3806","affiliations":[{"raw_affiliation_string":"Integrated Systems Laboratory (IIS), ETH Zurich, Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]},{"raw_affiliation_string":"Department of Electrical, Electronic and Information Engineering (DEI), University of Bologna, Bologna, Italy","institution_ids":["https://openalex.org/I9360294"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.3212,"has_fulltext":true,"cited_by_count":22,"citation_normalized_percentile":{"value":0.96893172,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"73","issue":"7","first_page":"1822","last_page":"1836"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.7820000052452087,"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"}},"topics":[{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.7820000052452087,"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":0.6746383309364319},{"id":"https://openalex.org/keywords/core","display_name":"Core (optical fiber)","score":0.5565553903579712},{"id":"https://openalex.org/keywords/open-source","display_name":"Open source","score":0.5532934069633484},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.5495733022689819},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.38729310035705566},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.21982812881469727},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1429193913936615},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.06783649325370789}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6746383309364319},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.5565553903579712},{"id":"https://openalex.org/C3018397939","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Open source","level":3,"score":0.5532934069633484},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.5495733022689819},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.38729310035705566},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.21982812881469727},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1429193913936615},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.06783649325370789}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tc.2024.3388896","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tc.2024.3388896","pdf_url":null,"source":{"id":"https://openalex.org/S157670870","display_name":"IEEE Transactions on Computers","issn_l":"0018-9340","issn":["0018-9340","1557-9956","2326-3814"],"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 Computers","raw_type":"journal-article"},{"id":"pmh:oai:cris.unibo.it:11585/1004690","is_oa":true,"landing_page_url":"https://hdl.handle.net/11585/1004690","pdf_url":"https://cris.unibo.it/bitstream/11585/1004690/3/2311.07493v2.pdf","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/article"}],"best_oa_location":{"id":"pmh:oai:cris.unibo.it:11585/1004690","is_oa":true,"landing_page_url":"https://hdl.handle.net/11585/1004690","pdf_url":"https://cris.unibo.it/bitstream/11585/1004690/3/2311.07493v2.pdf","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/article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322183","display_name":"Huawei Technologies","ror":"https://ror.org/00cmhce21"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4394805411.pdf","grobid_xml":"https://content.openalex.org/works/W4394805411.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W2026070376","https://openalex.org/W2144481293","https://openalex.org/W2994193159","https://openalex.org/W3013692244","https://openalex.org/W3042944763","https://openalex.org/W3090225637","https://openalex.org/W3095806684","https://openalex.org/W3102724434","https://openalex.org/W3105514082","https://openalex.org/W3178105557","https://openalex.org/W3183374399","https://openalex.org/W3196188193","https://openalex.org/W3213407904","https://openalex.org/W4286563542","https://openalex.org/W4307079523","https://openalex.org/W4311995762","https://openalex.org/W4387064016","https://openalex.org/W4388581261"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W1993191611","https://openalex.org/W2023938924","https://openalex.org/W2918840249","https://openalex.org/W1991859582","https://openalex.org/W2110053126","https://openalex.org/W2079303253","https://openalex.org/W2104702637","https://openalex.org/W4248099758"],"abstract_inverted_index":{"Vector":[0],"processing":[1],"is":[2],"highly":[3],"effective":[4],"in":[5,97],"boosting":[6],"processor":[7,25],"performance":[8,37,67,86,141,181],"and":[9,49,69,76,110,114,127,142],"efficiency":[10,122],"for":[11,45],"data-parallel":[12,43],"workloads.":[13],"In":[14],"this":[15],"paper,":[16],"we":[17,94,138,149],"present":[18],"Ara2,":[19],"the":[20,28,60,72,82,89,92,140,157],"first":[21],"fully":[22],"open-source":[23],"vector":[24,77,84,147,153],"to":[26],"support":[27],"RISC-V":[29],"V":[30],"1.0":[31],"frozen":[32],"ISA.":[33],"We":[34,65],"evaluate":[35],"Ara2\u2019s":[36],"on":[38,59,105],"a":[39,98,119,168,183,191],"diverse":[40],"set":[41],"of":[42,57,91,123,129,145,170],"kernels":[44],"various":[46,106],"problem":[47],"sizes":[48],"vector-unit":[50],"configurations,":[51],"achieving":[52],"an":[53],"average":[54],"functional-unit":[55],"utilization":[56],"95%":[58],"most":[61],"computationally":[62],"intensive":[63],"kernels.":[64],"pinpoint":[66],"boosters":[68],"bottlenecks,":[70],"including":[71],"scalar":[73,158],"core,":[74],"memories,":[75],"architecture,":[78],"providing":[79],"insights":[80],"into":[81],"main":[83],"architecture\u2019s":[85],"drivers.":[87],"Leveraging":[88],"openness":[90],"design,":[93],"implement":[95],"Ara2":[96,117,173,186],"22nm":[99],"technology,":[100],"characterize":[101],"its":[102,112],"PPA":[103],"metrics":[104],"configurations":[107],"(2-16":[108],"lanes),":[109],"analyze":[111],"microarchitecture":[113],"implementation":[115],"bottlenecks.":[116],"achieves":[118,176],"state-of-the-art":[120],"energy":[121,198],"37.8":[124],"DP-GFLOPS/W":[125],"(0.8V)":[126],"1.35GHz":[128],"clock":[130],"frequency":[131],"(critical":[132],"path:":[133],"~40":[134],"FO4":[135],"gates).":[136],"Finally,":[137],"explore":[139],"energy-efficiency":[143],"trade-offs":[144],"multi-core":[146],"processors:":[148],"find":[150],"that":[151,162],"multiple":[152],"cores":[154],"help":[155],"overcome":[156],"core":[159],"issue-rate":[160],"bound":[161],"limits":[163],"short-vector":[164],"performance.":[165],"For":[166],"example,":[167],"cluster":[169],"eight":[171],"2-lane":[172],"(16":[174,187],"FPUs)":[175,188],"more":[177],"than":[178,182],"3x":[179],"better":[180],"16-lane":[184],"single-core":[185],"when":[189],"executing":[190],"32x32x32":[192],"matrix":[193],"multiplication,":[194],"with":[195],"1.5x":[196],"improved":[197],"efficiency.":[199]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-19T17:40:00.097472","created_date":"2025-10-10T00:00:00"}
