{"id":"https://openalex.org/W7165126273","doi":"https://doi.org/10.1145/3787109.3815294","title":"AsymVPU: A Scalable and Area-Efficient Vector Architecture via Intra-Lane Asymmetry and Hierarchical Co-Design","display_name":"AsymVPU: A Scalable and Area-Efficient Vector Architecture via Intra-Lane Asymmetry and Hierarchical Co-Design","publication_year":2026,"publication_date":"2026-06-18","ids":{"openalex":"https://openalex.org/W7165126273","doi":"https://doi.org/10.1145/3787109.3815294"},"language":null,"primary_location":{"id":"doi:10.1145/3787109.3815294","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3787109.3815294","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Great Lakes Symposium on VLSI 2026","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3787109.3815294","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5121169731","display_name":"Junzhe Jing","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junzhe Jing","raw_affiliation_strings":["Research Center for Intelligent Computing Systems, SKLP, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0009-5662-3366","affiliations":[{"raw_affiliation_string":"Research Center for Intelligent Computing Systems, SKLP, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100427695","display_name":"Bowen Liu","orcid":"https://orcid.org/0000-0002-4194-8119"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bowen Liu","raw_affiliation_strings":["Research Center for Intelligent Computing Systems, SKLP, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0007-1061-9703","affiliations":[{"raw_affiliation_string":"Research Center for Intelligent Computing Systems, SKLP, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081240542","display_name":"Min Feng","orcid":"https://orcid.org/0000-0002-0107-0196"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Min","raw_affiliation_strings":["Research Center for Intelligent Computing Systems, SKLP, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-0107-0196","affiliations":[{"raw_affiliation_string":"Research Center for Intelligent Computing Systems, SKLP, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100633632","display_name":"Yue Wang","orcid":"https://orcid.org/0000-0003-0098-5359"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Wang","raw_affiliation_strings":["Research Center for Intelligent Computing Systems, SKLP, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-1636-5878","affiliations":[{"raw_affiliation_string":"Research Center for Intelligent Computing Systems, SKLP, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016864694","display_name":"Yinhe Han","orcid":"https://orcid.org/0000-0003-0904-6681"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yinhe Han","raw_affiliation_strings":["Research Center for Intelligent Computing Systems, SKLP, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-0904-6681","affiliations":[{"raw_affiliation_string":"Research Center for Intelligent Computing Systems, SKLP, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210090176"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.9082083,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"967","last_page":"974"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.5738999843597412,"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"}},"topics":[{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.5738999843597412,"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"}},{"id":"https://openalex.org/T10904","display_name":"Embedded Systems Design Techniques","score":0.12160000205039978,"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"}},{"id":"https://openalex.org/T10363","display_name":"Low-power high-performance VLSI design","score":0.08910000324249268,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.71670001745224},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6467000246047974},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.4300999939441681},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.4115000069141388},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.3702000081539154},{"id":"https://openalex.org/keywords/vector-processor","display_name":"Vector processor","score":0.3343000113964081}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7498000264167786},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.71670001745224},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6467000246047974},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.48809999227523804},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.438400000333786},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.4300999939441681},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.4115000069141388},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.3702000081539154},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3617999851703644},{"id":"https://openalex.org/C161824985","wikidata":"https://www.wikidata.org/wiki/Q919509","display_name":"Vector processor","level":2,"score":0.3343000113964081},{"id":"https://openalex.org/C106515295","wikidata":"https://www.wikidata.org/wiki/Q26806595","display_name":"Parallel processing","level":2,"score":0.31060001254081726},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.2849999964237213},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.2797999978065491},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.2660999894142151},{"id":"https://openalex.org/C200288055","wikidata":"https://www.wikidata.org/wiki/Q2621792","display_name":"Element (criminal law)","level":2,"score":0.25949999690055847},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.25540000200271606}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3787109.3815294","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3787109.3815294","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Great Lakes Symposium on VLSI 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3787109.3815294","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3787109.3815294","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Great Lakes Symposium on VLSI 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.4070269763469696,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[{"id":"https://openalex.org/G2568771357","display_name":null,"funder_award_id":"U24A20291","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W2055312318","https://openalex.org/W2994193159","https://openalex.org/W4410583083","https://openalex.org/W4415309624"],"related_works":[],"abstract_inverted_index":{"Modern":[0],"AI":[1],"inference":[2],"interleaves":[3],"compute-dense":[4],"matrix":[5],"kernels":[6],"with":[7,20,76],"memory-sensitive":[8],"element-wise":[9],"and":[10,87,100,125],"reduction":[11,80,128],"operators.":[12],"Symmetric":[13],"RISC-V":[14],"vector":[15,44,69],"processors":[16],"execute":[17],"this":[18,73],"mix":[19],"a":[21,41,77,82,103],"uniform":[22],"lane":[23,74],"design,":[24],"replicating":[25],"heavy":[26],"arithmetic":[27],"units":[28],"even":[29],"when":[30],"many":[31],"instructions":[32],"need":[33],"only":[34],"lightweight":[35,68],"arithmetic.":[36],"This":[37],"paper":[38],"presents":[39],"AsymVPU,":[40],"hardware-software":[42],"co-designed":[43],"architecture":[45],"that":[46,91],"introduces":[47],"fine-grained":[48],"intra-lane":[49],"asymmetry:":[50],"one":[51],"main":[52],"processing":[53,62],"element":[54],"retains":[55],"full":[56],"FP64/FMA":[57],"capability,":[58],"while":[59,130],"three":[60],"auxiliary":[61],"elements":[63],"provide":[64],"dense":[65],"support":[66],"for":[67,122],"operations.":[70],"AsymVPU":[71,113],"couples":[72],"organization":[75],"two-level":[78],"hierarchical":[79],"network,":[81],"coordinated":[83],"global":[84],"load/store":[85],"path,":[86],"compiler-inserted":[88],"density":[89,121],"hints":[90],"preserve":[92],"the":[93],"RVV":[94],"programming":[95],"abstraction.":[96],"Implemented":[97],"in":[98,102],"SystemVerilog":[99],"evaluated":[101],"same-flow":[104],"12":[105],"nm":[106],"comparison":[107],"against":[108],"an":[109],"Ara-derived":[110],"symmetric":[111],"baseline,":[112],"achieves":[114],"up":[115],"to":[116],"2.4":[117],"\u00d7":[118],"higher":[119],"compute":[120],"quantized":[123],"workloads":[124],"60%":[126],"lower":[127],"latency,":[129],"retaining":[131],"competitive":[132],"performance":[133],"on":[134],"FMA-dominated":[135],"kernels.":[136]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2026-06-19T00:00:00"}