{"id":"https://openalex.org/W4414197826","doi":"https://doi.org/10.1109/dac63849.2025.11133317","title":"An Energy-Efficient High-Utilization Hardware Architecture for Attention Mechanism in Transformer using Balanced Systolic Array and Multi-Row Interleaved Operation Ordering","display_name":"An Energy-Efficient High-Utilization Hardware Architecture for Attention Mechanism in Transformer using Balanced Systolic Array and Multi-Row Interleaved Operation Ordering","publication_year":2025,"publication_date":"2025-06-22","ids":{"openalex":"https://openalex.org/W4414197826","doi":"https://doi.org/10.1109/dac63849.2025.11133317"},"language":"en","primary_location":{"id":"doi:10.1109/dac63849.2025.11133317","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dac63849.2025.11133317","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 62nd ACM/IEEE Design Automation Conference (DAC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5101390899","display_name":"Haiyang Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090209","display_name":"Institute of Microelectronics","ror":"https://ror.org/009rw8n36","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I4210090209","https://openalex.org/I91275662"]},{"id":"https://openalex.org/I4210119392","display_name":"Institute of Microelectronics","ror":"https://ror.org/02s6gs133","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210119392"]}],"countries":["CN","SG"],"is_corresponding":false,"raw_author_name":"Haiyang Zhou","raw_affiliation_strings":["Institute of Microelectronics of Chinese Academy of Sciences,Key Laboratory of Fabrication Technologies for Integrated Circuits,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Microelectronics of Chinese Academy of Sciences,Key Laboratory of Fabrication Technologies for Integrated Circuits,Beijing,China","institution_ids":["https://openalex.org/I4210090209","https://openalex.org/I4210119392"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101546412","display_name":"Hongyang Hu","orcid":"https://orcid.org/0000-0003-2291-9598"},"institutions":[{"id":"https://openalex.org/I4210090209","display_name":"Institute of Microelectronics","ror":"https://ror.org/009rw8n36","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I4210090209","https://openalex.org/I91275662"]},{"id":"https://openalex.org/I4210119392","display_name":"Institute of Microelectronics","ror":"https://ror.org/02s6gs133","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210119392"]}],"countries":["CN","SG"],"is_corresponding":false,"raw_author_name":"Hongyang Hu","raw_affiliation_strings":["Institute of Microelectronics of Chinese Academy of Sciences,Key Laboratory of Fabrication Technologies for Integrated Circuits,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Microelectronics of Chinese Academy of Sciences,Key Laboratory of Fabrication Technologies for Integrated Circuits,Beijing,China","institution_ids":["https://openalex.org/I4210090209","https://openalex.org/I4210119392"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053627404","display_name":"Jinshan Yue","orcid":"https://orcid.org/0000-0001-8234-7400"},"institutions":[{"id":"https://openalex.org/I4210090209","display_name":"Institute of Microelectronics","ror":"https://ror.org/009rw8n36","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I4210090209","https://openalex.org/I91275662"]},{"id":"https://openalex.org/I4210119392","display_name":"Institute of Microelectronics","ror":"https://ror.org/02s6gs133","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210119392"]}],"countries":["CN","SG"],"is_corresponding":false,"raw_author_name":"Jinshan Yue","raw_affiliation_strings":["Institute of Microelectronics of Chinese Academy of Sciences,Key Laboratory of Fabrication Technologies for Integrated Circuits,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Microelectronics of Chinese Academy of Sciences,Key Laboratory of Fabrication Technologies for Integrated Circuits,Beijing,China","institution_ids":["https://openalex.org/I4210090209","https://openalex.org/I4210119392"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085120100","display_name":"Hanghang Gao","orcid":"https://orcid.org/0009-0006-3434-5682"},"institutions":[{"id":"https://openalex.org/I4210090209","display_name":"Institute of Microelectronics","ror":"https://ror.org/009rw8n36","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I4210090209","https://openalex.org/I91275662"]},{"id":"https://openalex.org/I4210119392","display_name":"Institute of Microelectronics","ror":"https://ror.org/02s6gs133","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210119392"]}],"countries":["CN","SG"],"is_corresponding":false,"raw_author_name":"Hanghang Gao","raw_affiliation_strings":["Institute of Microelectronics of Chinese Academy of Sciences,Key Laboratory of Fabrication Technologies for Integrated Circuits,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Microelectronics of Chinese Academy of Sciences,Key Laboratory of Fabrication Technologies for Integrated Circuits,Beijing,China","institution_ids":["https://openalex.org/I4210090209","https://openalex.org/I4210119392"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101316374","display_name":"Yuanlu Xie","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090209","display_name":"Institute of Microelectronics","ror":"https://ror.org/009rw8n36","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I4210090209","https://openalex.org/I91275662"]},{"id":"https://openalex.org/I4210119392","display_name":"Institute of Microelectronics","ror":"https://ror.org/02s6gs133","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210119392"]}],"countries":["CN","SG"],"is_corresponding":false,"raw_author_name":"Yuanlu Xie","raw_affiliation_strings":["Institute of Microelectronics of Chinese Academy of Sciences,Key Laboratory of Fabrication Technologies for Integrated Circuits,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Microelectronics of Chinese Academy of Sciences,Key Laboratory of Fabrication Technologies for Integrated Circuits,Beijing,China","institution_ids":["https://openalex.org/I4210090209","https://openalex.org/I4210119392"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049920459","display_name":"Xiaoxin Xu","orcid":"https://orcid.org/0000-0002-0277-1314"},"institutions":[{"id":"https://openalex.org/I4210090209","display_name":"Institute of Microelectronics","ror":"https://ror.org/009rw8n36","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I4210090209","https://openalex.org/I91275662"]},{"id":"https://openalex.org/I4210119392","display_name":"Institute of Microelectronics","ror":"https://ror.org/02s6gs133","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210119392"]}],"countries":["CN","SG"],"is_corresponding":false,"raw_author_name":"Xiaoxin Xu","raw_affiliation_strings":["Institute of Microelectronics of Chinese Academy of Sciences,Key Laboratory of Fabrication Technologies for Integrated Circuits,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Microelectronics of Chinese Academy of Sciences,Key Laboratory of Fabrication Technologies for Integrated Circuits,Beijing,China","institution_ids":["https://openalex.org/I4210090209","https://openalex.org/I4210119392"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063861198","display_name":"Chunmeng Dou","orcid":"https://orcid.org/0000-0003-2192-9655"},"institutions":[{"id":"https://openalex.org/I4210090209","display_name":"Institute of Microelectronics","ror":"https://ror.org/009rw8n36","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I4210090209","https://openalex.org/I91275662"]},{"id":"https://openalex.org/I4210119392","display_name":"Institute of Microelectronics","ror":"https://ror.org/02s6gs133","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210119392"]}],"countries":["CN","SG"],"is_corresponding":false,"raw_author_name":"Chunmeng Dou","raw_affiliation_strings":["Institute of Microelectronics of Chinese Academy of Sciences,Key Laboratory of Fabrication Technologies for Integrated Circuits,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Microelectronics of Chinese Academy of Sciences,Key Laboratory of Fabrication Technologies for Integrated Circuits,Beijing,China","institution_ids":["https://openalex.org/I4210090209","https://openalex.org/I4210119392"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100347764","display_name":"Ming Liu","orcid":"https://orcid.org/0000-0002-0937-7547"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ming Liu","raw_affiliation_strings":["Fudan University,Frontier Institute of Chip and System,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University,Frontier Institute of Chip and System,Shanghai,China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13183","display_name":"Islanding Detection in Power Systems","score":0.9818000197410583,"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"}},"topics":[{"id":"https://openalex.org/T13183","display_name":"Islanding Detection in Power Systems","score":0.9818000197410583,"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/T11343","display_name":"Power Transformer Diagnostics and Insulation","score":0.9807000160217285,"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/T10573","display_name":"Power Quality and Harmonics","score":0.9775999784469604,"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/efficient-energy-use","display_name":"Efficient energy use","score":0.6650000214576721},{"id":"https://openalex.org/keywords/systolic-array","display_name":"Systolic array","score":0.6263999938964844},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.6057000160217285},{"id":"https://openalex.org/keywords/static-random-access-memory","display_name":"Static random-access memory","score":0.4973999857902527},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.4837000072002411},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4510999917984009},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.4424000084400177}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7139999866485596},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.6650000214576721},{"id":"https://openalex.org/C150741067","wikidata":"https://www.wikidata.org/wiki/Q2377218","display_name":"Systolic array","level":3,"score":0.6263999938964844},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.6057000160217285},{"id":"https://openalex.org/C68043766","wikidata":"https://www.wikidata.org/wiki/Q267416","display_name":"Static random-access memory","level":2,"score":0.4973999857902527},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.4837000072002411},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.4706000089645386},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4510999917984009},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.4487000107765198},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.4424000084400177},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.42329999804496765},{"id":"https://openalex.org/C2780165032","wikidata":"https://www.wikidata.org/wiki/Q16869822","display_name":"Energy consumption","level":2,"score":0.41659998893737793},{"id":"https://openalex.org/C13164978","wikidata":"https://www.wikidata.org/wiki/Q600158","display_name":"Hardware acceleration","level":3,"score":0.39399999380111694},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3190999925136566},{"id":"https://openalex.org/C2994168587","wikidata":"https://www.wikidata.org/wiki/Q5295","display_name":"Random access memory","level":2,"score":0.2980000078678131},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.29660001397132874},{"id":"https://openalex.org/C46637626","wikidata":"https://www.wikidata.org/wiki/Q6693015","display_name":"Low latency (capital markets)","level":2,"score":0.2888000011444092},{"id":"https://openalex.org/C2989164559","wikidata":"https://www.wikidata.org/wiki/Q15637420","display_name":"Low energy","level":2,"score":0.27730000019073486},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.26190000772476196}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/dac63849.2025.11133317","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dac63849.2025.11133317","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 62nd ACM/IEEE Design Automation Conference (DAC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W2289252105","https://openalex.org/W3016832937","https://openalex.org/W3017024317","https://openalex.org/W3017059173","https://openalex.org/W3159727696","https://openalex.org/W3189877953","https://openalex.org/W4293025165","https://openalex.org/W4313467238","https://openalex.org/W4360831795","https://openalex.org/W4380881077","https://openalex.org/W4385245566","https://openalex.org/W4386763770","https://openalex.org/W4390097310"],"related_works":[],"abstract_inverted_index":{"Transformer-based":[0],"neural":[1],"networks":[2],"have":[3],"achieved":[4],"remarkable":[5],"performance.":[6],"Designing":[7],"energy-efficient":[8,103],"and":[9,20,40,84,96,104,142,182],"high-speed":[10],"accelerators":[11,30,48],"for":[12,60],"the":[13,18,69,77,122,127,151,162,171],"attention":[14,29,74,173],"mechanism,":[15],"which":[16,98,131,160],"dominates":[17],"energy":[19,38,133,164,180],"latency":[21],"in":[22,68,179,186],"Transformers,":[23],"has":[24],"become":[25],"increasingly":[26],"significant.":[27],"Existing":[28],"commonly":[31],"use":[32],"algorithm-hardware":[33],"co-design":[34],"to":[35,100,138,190],"achieve":[36],"higher":[37],"efficiency":[39,134,181,188],"speed.":[41],"However,":[42],"deeply":[43],"customized":[44],"algorithms":[45],"make":[46],"these":[47],"dependent":[49],"on":[50],"a":[51,144,176,183],"particular":[52],"application.":[53],"Therefore,":[54],"optimizing":[55],"hardware":[56,70],"architecture":[57,71],"is":[58],"crucial":[59],"achieving":[61],"general-purpose":[62],"acceleration.":[63],"We":[64],"observe":[65],"two":[66,169],"limitations":[67],"of":[72,117,147],"existing":[73],"accelerators.":[75,107],"First,":[76],"widely":[78],"used":[79],"input":[80],"stationary,":[81,83],"weight":[82],"output":[85],"stationary":[86],"systolic":[87,140],"arrays":[88,141],"(SAs)":[89],"can\u2019t":[90],"balance":[91],"data":[92],"reuse,":[93],"register":[94],"saving,":[95],"utilization,":[97],"hinders":[99],"build":[101],"more":[102],"faster":[105],"SA-based":[106],"Second,":[108],"layer-by-layer":[109],"operation":[110,158],"ordering":[111],"introduces":[112],"high":[113],"SRAM":[114,163],"access":[115],"overhead":[116],"intermediate":[118],"results.":[119],"To":[120,149],"address":[121,150],"first":[123],"limitation,":[124,153],"we":[125,154],"propose":[126,155],"\u201cBalanced":[128],"Systolic":[129],"Array\u201d,":[130],"improves":[132],"by":[135,165],"40%":[136],"compared":[137,189],"conventional":[139],"achieves":[143,175],"utilization":[145],"rate":[146],"99.5%.":[148],"second":[152],"\u201cMulti-Row":[156],"Interleaved\u201d":[157],"ordering,":[159],"reduces":[161],"31.7%":[166],"By":[167],"integrating":[168],"techniques,":[170],"proposed":[172],"accelerator":[174],"39%":[177],"improvement":[178],"38%":[184],"enhancement":[185],"throughput\u00d7energy":[187],"previous":[191],"works.":[192]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
