{"id":"https://openalex.org/W4412985124","doi":"https://doi.org/10.1109/les.2025.3595586","title":"An Agile Systolic Array-Based Hardware Accelerator for Scalable Multi-Head Self-Attention","display_name":"An Agile Systolic Array-Based Hardware Accelerator for Scalable Multi-Head Self-Attention","publication_year":2025,"publication_date":"2025-08-05","ids":{"openalex":"https://openalex.org/W4412985124","doi":"https://doi.org/10.1109/les.2025.3595586"},"language":"en","primary_location":{"id":"doi:10.1109/les.2025.3595586","is_oa":false,"landing_page_url":"https://doi.org/10.1109/les.2025.3595586","pdf_url":null,"source":{"id":"https://openalex.org/S22443479","display_name":"IEEE Embedded Systems Letters","issn_l":"1943-0663","issn":["1943-0663","1943-0671"],"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 Embedded Systems Letters","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5038703876","display_name":"Xinyu Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinyu Chen","raw_affiliation_strings":["Shanghai Key Laboratory of Chips and Systems for Intelligent Connected Vehicle and the School of Communication and Information Engineering, Shanghai University, Shanghai, China","Shanghai Key Laboratory of Chips and Systems for Intelligent Connected Vehicle and School of Communication and Information Engineering, Shanghai University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0008-4717-1962","affiliations":[{"raw_affiliation_string":"Shanghai Key Laboratory of Chips and Systems for Intelligent Connected Vehicle and the School of Communication and Information Engineering, Shanghai University, Shanghai, China","institution_ids":["https://openalex.org/I113940042"]},{"raw_affiliation_string":"Shanghai Key Laboratory of Chips and Systems for Intelligent Connected Vehicle and School of Communication and Information Engineering, Shanghai University, Shanghai, China","institution_ids":["https://openalex.org/I113940042"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100345873","display_name":"Yu Li","orcid":"https://orcid.org/0000-0002-9439-8421"},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Li","raw_affiliation_strings":["Shanghai Key Laboratory of Chips and Systems for Intelligent Connected Vehicle and the School of Communication and Information Engineering, Shanghai University, Shanghai, China","Shanghai Key Laboratory of Chips and Systems for Intelligent Connected Vehicle and School of Communication and Information Engineering, Shanghai University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Key Laboratory of Chips and Systems for Intelligent Connected Vehicle and the School of Communication and Information Engineering, Shanghai University, Shanghai, China","institution_ids":["https://openalex.org/I113940042"]},{"raw_affiliation_string":"Shanghai Key Laboratory of Chips and Systems for Intelligent Connected Vehicle and School of Communication and Information Engineering, Shanghai University, Shanghai, China","institution_ids":["https://openalex.org/I113940042"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111246382","display_name":"Beining Zhao","orcid":"https://orcid.org/0009-0006-4550-7974"},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Beining Zhao","raw_affiliation_strings":["Shanghai Key Laboratory of Chips and Systems for Intelligent Connected Vehicle and the School of Communication and Information Engineering, Shanghai University, Shanghai, China","Shanghai Key Laboratory of Chips and Systems for Intelligent Connected Vehicle and School of Communication and Information Engineering, Shanghai University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0006-4550-7974","affiliations":[{"raw_affiliation_string":"Shanghai Key Laboratory of Chips and Systems for Intelligent Connected Vehicle and the School of Communication and Information Engineering, Shanghai University, Shanghai, China","institution_ids":["https://openalex.org/I113940042"]},{"raw_affiliation_string":"Shanghai Key Laboratory of Chips and Systems for Intelligent Connected Vehicle and School of Communication and Information Engineering, Shanghai University, Shanghai, China","institution_ids":["https://openalex.org/I113940042"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031702833","display_name":"Yintao Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yintao Liu","raw_affiliation_strings":["Shanghai Key Laboratory of Chips and Systems for Intelligent Connected Vehicle and the School of Communication and Information Engineering, Shanghai University, Shanghai, China","Shanghai Key Laboratory of Chips and Systems for Intelligent Connected Vehicle and School of Communication and Information Engineering, Shanghai University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0002-3538-4676","affiliations":[{"raw_affiliation_string":"Shanghai Key Laboratory of Chips and Systems for Intelligent Connected Vehicle and the School of Communication and Information Engineering, Shanghai University, Shanghai, China","institution_ids":["https://openalex.org/I113940042"]},{"raw_affiliation_string":"Shanghai Key Laboratory of Chips and Systems for Intelligent Connected Vehicle and School of Communication and Information Engineering, Shanghai University, Shanghai, China","institution_ids":["https://openalex.org/I113940042"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044419947","display_name":"Shan Cao","orcid":"https://orcid.org/0000-0003-3713-8671"},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shan Cao","raw_affiliation_strings":["Shanghai Key Laboratory of Chips and Systems for Intelligent Connected Vehicle and the School of Communication and Information Engineering, Shanghai University, Shanghai, China","Shanghai Key Laboratory of Chips and Systems for Intelligent Connected Vehicle and School of Communication and Information Engineering, Shanghai University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-3713-8671","affiliations":[{"raw_affiliation_string":"Shanghai Key Laboratory of Chips and Systems for Intelligent Connected Vehicle and the School of Communication and Information Engineering, Shanghai University, Shanghai, China","institution_ids":["https://openalex.org/I113940042"]},{"raw_affiliation_string":"Shanghai Key Laboratory of Chips and Systems for Intelligent Connected Vehicle and School of Communication and Information Engineering, Shanghai University, Shanghai, China","institution_ids":["https://openalex.org/I113940042"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008150938","display_name":"Zhiyuan Jiang","orcid":"https://orcid.org/0000-0002-8522-5721"},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyuan Jiang","raw_affiliation_strings":["Shanghai Key Laboratory of Chips and Systems for Intelligent Connected Vehicle and the School of Communication and Information Engineering, Shanghai University, Shanghai, China","Shanghai Key Laboratory of Chips and Systems for Intelligent Connected Vehicle and School of Communication and Information Engineering, Shanghai University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-8522-5721","affiliations":[{"raw_affiliation_string":"Shanghai Key Laboratory of Chips and Systems for Intelligent Connected Vehicle and the School of Communication and Information Engineering, Shanghai University, Shanghai, China","institution_ids":["https://openalex.org/I113940042"]},{"raw_affiliation_string":"Shanghai Key Laboratory of Chips and Systems for Intelligent Connected Vehicle and School of Communication and Information Engineering, Shanghai University, Shanghai, China","institution_ids":["https://openalex.org/I113940042"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I113940042"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16845842,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"18","issue":"2","first_page":"90","last_page":"93"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10904","display_name":"Embedded Systems Design Techniques","score":0.9623000025749207,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9623000025749207,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9174000024795532,"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/computer-science","display_name":"Computer science","score":0.8315200209617615},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6485637426376343},{"id":"https://openalex.org/keywords/systolic-array","display_name":"Systolic array","score":0.5948847532272339},{"id":"https://openalex.org/keywords/agile-software-development","display_name":"Agile software development","score":0.572344183921814},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.47258460521698},{"id":"https://openalex.org/keywords/head","display_name":"Head (geology)","score":0.42816218733787537},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.40883997082710266},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.17398759722709656},{"id":"https://openalex.org/keywords/very-large-scale-integration","display_name":"Very-large-scale integration","score":0.13792684674263},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.12818098068237305}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8315200209617615},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6485637426376343},{"id":"https://openalex.org/C150741067","wikidata":"https://www.wikidata.org/wiki/Q2377218","display_name":"Systolic array","level":3,"score":0.5948847532272339},{"id":"https://openalex.org/C14185376","wikidata":"https://www.wikidata.org/wiki/Q30232","display_name":"Agile software development","level":2,"score":0.572344183921814},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.47258460521698},{"id":"https://openalex.org/C2780312720","wikidata":"https://www.wikidata.org/wiki/Q5689100","display_name":"Head (geology)","level":2,"score":0.42816218733787537},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.40883997082710266},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.17398759722709656},{"id":"https://openalex.org/C14580979","wikidata":"https://www.wikidata.org/wiki/Q876049","display_name":"Very-large-scale integration","level":2,"score":0.13792684674263},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.12818098068237305},{"id":"https://openalex.org/C114793014","wikidata":"https://www.wikidata.org/wiki/Q52109","display_name":"Geomorphology","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/les.2025.3595586","is_oa":false,"landing_page_url":"https://doi.org/10.1109/les.2025.3595586","pdf_url":null,"source":{"id":"https://openalex.org/S22443479","display_name":"IEEE Embedded Systems Letters","issn_l":"1943-0663","issn":["1943-0663","1943-0671"],"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 Embedded Systems Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2488712091","display_name":null,"funder_award_id":"12141107","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2615687763","display_name":null,"funder_award_id":"24DP1501100","funder_id":"https://openalex.org/F4320327061","funder_display_name":"Shanghai Minhang Science and Technology Commission"},{"id":"https://openalex.org/G3889144995","display_name":null,"funder_award_id":"62271300","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4888131337","display_name":null,"funder_award_id":"24DP1500600","funder_id":"https://openalex.org/F4320327061","funder_display_name":"Shanghai Minhang Science and Technology Commission"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320327061","display_name":"Shanghai Minhang Science and Technology Commission","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4240320454","https://openalex.org/W2070314832","https://openalex.org/W2395557210","https://openalex.org/W2656997359","https://openalex.org/W2010232134","https://openalex.org/W2389214306","https://openalex.org/W4240110559","https://openalex.org/W2384485649","https://openalex.org/W2094372386","https://openalex.org/W1973385172"],"abstract_inverted_index":{"As":[0,25],"attention":[1,20],"mechanisms":[2],"find":[3],"increasing":[4],"application":[5],"in":[6,73,149],"computer":[7],"vision,":[8],"numerous":[9],"neural":[10,16],"networks":[11,17],"are":[12],"now":[13],"integrating":[14],"convolutional":[15],"(CNNs)":[18],"with":[19],"layers":[21],"to":[22,47,100,140],"enhance":[23],"performance.":[24],"a":[26,65,82,94,111,127,133,146],"typical":[27],"representative,":[28],"the":[29,36,52,86,123],"Bottleneck":[30],"Transformer":[31],"(BoT)":[32],"network":[33],"effectively":[34],"balances":[35],"extraction":[37],"of":[38,43,57,68,89,129,135],"local":[39],"features":[40],"and":[41,76,110],"modeling":[42],"global":[44],"context,":[45],"leading":[46],"significant":[48],"performance":[49,128],"improvements.":[50],"However,":[51],"multi-head":[53],"self-attention":[54],"(MHSA)":[55],"layer":[56,88],"BoT":[58],"deviates":[59],"from":[60],"conventional":[61],"MHSA":[62,87,117],"by":[63],"incorporating":[64],"wider":[66],"range":[67],"matrix":[69,103,106],"operations,":[70,104],"posing":[71],"challenges":[72],"computational":[74],"complexity":[75],"memory":[77],"bandwidth.":[78],"This":[79],"letter":[80],"introduces":[81],"customized":[83],"accelerator":[84,92,125],"for":[85],"BoT.":[90],"The":[91],"employs":[93],"configurable":[95],"systolic":[96],"array":[97],"architecture,":[98],"designed":[99],"support":[101],"various":[102],"including":[105],"transposition,":[107],"addition,":[108],"multiplication,":[109],"hardware-optimized":[112],"Softmax,":[113],"facilitating":[114],"hybrid":[115],"scalable":[116],"layers.":[118],"Implemented":[119],"on":[120],"an":[121],"FPGA,":[122],"proposed":[124],"achieves":[126],"143.98":[130],"GOPS":[131],"at":[132],"frequency":[134],"320":[136],"MHz.":[137],"When":[138],"compared":[139],"CPU":[141],"implementations,":[142],"our":[143],"design":[144],"offers":[145],"7.18\u00d7":[147],"reduction":[148],"inference":[150],"time.":[151]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}