{"id":"https://openalex.org/W4214686755","doi":"https://doi.org/10.1145/3503222.3507738","title":"DOTA: detect and omit weak attentions for scalable transformer acceleration","display_name":"DOTA: detect and omit weak attentions for scalable transformer acceleration","publication_year":2022,"publication_date":"2022-02-22","ids":{"openalex":"https://openalex.org/W4214686755","doi":"https://doi.org/10.1145/3503222.3507738"},"language":"en","primary_location":{"id":"doi:10.1145/3503222.3507738","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3503222.3507738","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3503222.3507738","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 27th ACM International Conference on Architectural Support for Programming Languages and Operating Systems","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3503222.3507738","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5003935082","display_name":"Zheng Qu","orcid":"https://orcid.org/0000-0001-6574-0649"},"institutions":[{"id":"https://openalex.org/I154570441","display_name":"University of California, Santa Barbara","ror":"https://ror.org/02t274463","country_code":"US","type":"education","lineage":["https://openalex.org/I154570441"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zheng Qu","raw_affiliation_strings":["University of California at Santa Barbara, USA"],"affiliations":[{"raw_affiliation_string":"University of California at Santa Barbara, USA","institution_ids":["https://openalex.org/I154570441"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100324294","display_name":"Liu Liu","orcid":"https://orcid.org/0000-0003-0792-8146"},"institutions":[{"id":"https://openalex.org/I154570441","display_name":"University of California, Santa Barbara","ror":"https://ror.org/02t274463","country_code":"US","type":"education","lineage":["https://openalex.org/I154570441"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Liu Liu","raw_affiliation_strings":["University of California at Santa Barbara, USA"],"affiliations":[{"raw_affiliation_string":"University of California at Santa Barbara, USA","institution_ids":["https://openalex.org/I154570441"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038947607","display_name":"Fengbin Tu","orcid":"https://orcid.org/0000-0003-2228-8829"},"institutions":[{"id":"https://openalex.org/I154570441","display_name":"University of California, Santa Barbara","ror":"https://ror.org/02t274463","country_code":"US","type":"education","lineage":["https://openalex.org/I154570441"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fengbin Tu","raw_affiliation_strings":["University of California at Santa Barbara, USA"],"affiliations":[{"raw_affiliation_string":"University of California at Santa Barbara, USA","institution_ids":["https://openalex.org/I154570441"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037216840","display_name":"Zhaodong Chen","orcid":"https://orcid.org/0000-0001-9601-4586"},"institutions":[{"id":"https://openalex.org/I154570441","display_name":"University of California, Santa Barbara","ror":"https://ror.org/02t274463","country_code":"US","type":"education","lineage":["https://openalex.org/I154570441"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhaodong Chen","raw_affiliation_strings":["University of California at Santa Barbara, USA"],"affiliations":[{"raw_affiliation_string":"University of California at Santa Barbara, USA","institution_ids":["https://openalex.org/I154570441"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048052285","display_name":"Yufei Ding","orcid":"https://orcid.org/0000-0002-8716-5793"},"institutions":[{"id":"https://openalex.org/I154570441","display_name":"University of California, Santa Barbara","ror":"https://ror.org/02t274463","country_code":"US","type":"education","lineage":["https://openalex.org/I154570441"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yufei Ding","raw_affiliation_strings":["University of California at Santa Barbara, USA"],"affiliations":[{"raw_affiliation_string":"University of California at Santa Barbara, USA","institution_ids":["https://openalex.org/I154570441"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100385336","display_name":"Yuan Xie","orcid":"https://orcid.org/0000-0003-2093-1788"},"institutions":[{"id":"https://openalex.org/I154570441","display_name":"University of California, Santa Barbara","ror":"https://ror.org/02t274463","country_code":"US","type":"education","lineage":["https://openalex.org/I154570441"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuan Xie","raw_affiliation_strings":["University of California at Santa Barbara, USA"],"affiliations":[{"raw_affiliation_string":"University of California at Santa Barbara, USA","institution_ids":["https://openalex.org/I154570441"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5003935082"],"corresponding_institution_ids":["https://openalex.org/I154570441"],"apc_list":null,"apc_paid":null,"fwci":11.0246,"has_fulltext":true,"cited_by_count":115,"citation_normalized_percentile":{"value":0.99037513,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"14","last_page":"26"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.998199999332428,"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"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9948999881744385,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.7334669232368469},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6921440958976746},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6593723893165588},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6072497367858887},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5575971007347107},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.4992802143096924},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.4348231256008148},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.4246845841407776},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34556710720062256},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.32716408371925354},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.22122743725776672}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7334669232368469},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6921440958976746},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6593723893165588},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6072497367858887},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5575971007347107},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.4992802143096924},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.4348231256008148},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.4246845841407776},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34556710720062256},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.32716408371925354},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.22122743725776672},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3503222.3507738","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3503222.3507738","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3503222.3507738","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 27th ACM International Conference on Architectural Support for Programming Languages and Operating Systems","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-127230","is_oa":false,"landing_page_url":"http://lbdiscover.ust.hk/uresolver?url_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rfr_id=info:sid/HKUST:SPI&rft.genre=article&rft.issn=&rft.volume=&rft.issue=&rft.date=2022&rft.spage=14&rft.aulast=Qu&rft.aufirst=&rft.atitle=DOTA%3A+Detect+and+OmitWeak+Attentions+for+Scalable+Transformer+Acceleration&rft.title=International+Conference+on+Architectural+Support+for+Programming+Languages+and+Operating+Systems+-+ASPLOS","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference paper"}],"best_oa_location":{"id":"doi:10.1145/3503222.3507738","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3503222.3507738","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3503222.3507738","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 27th ACM International Conference on Architectural Support for Programming Languages and Operating Systems","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.8999999761581421,"id":"https://metadata.un.org/sdg/7"}],"awards":[{"id":"https://openalex.org/G1105249996","display_name":null,"funder_award_id":"DMR 1720256","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G1237365475","display_name":null,"funder_award_id":"DMR 1720256","funder_id":"https://openalex.org/F4320337367","funder_display_name":"Division of Materials Research"},{"id":"https://openalex.org/G1798702661","display_name":null,"funder_award_id":"MRSEC","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G1875027798","display_name":null,"funder_award_id":"MRSEC; NSF DMR 1720256","funder_id":"https://openalex.org/F4320337965","funder_display_name":"California NanoSystems Institute"},{"id":"https://openalex.org/G2045646697","display_name":null,"funder_award_id":"DMR 1720256","funder_id":"https://openalex.org/F4320333422","funder_display_name":"Materials Research Science and Engineering Center, Harvard University"},{"id":"https://openalex.org/G2300736770","display_name":null,"funder_award_id":"(CSC)","funder_id":"https://openalex.org/F4320322725","funder_display_name":"China Scholarship Council"},{"id":"https://openalex.org/G3282081486","display_name":null,"funder_award_id":"NSF DMR 1720256","funder_id":"https://openalex.org/F4320333422","funder_display_name":"Materials Research Science and Engineering Center, Harvard University"},{"id":"https://openalex.org/G4228342300","display_name":null,"funder_award_id":"NSF DMR 1720256","funder_id":"https://openalex.org/F4320332500","funder_display_name":"University of California, Santa Barbara"},{"id":"https://openalex.org/G4250104368","display_name":null,"funder_award_id":"1720256","funder_id":"https://openalex.org/F4320337367","funder_display_name":"Division of Materials Research"},{"id":"https://openalex.org/G428018807","display_name":null,"funder_award_id":"NSF 2124039","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5009579348","display_name":null,"funder_award_id":"MRSEC; NSF DMR 1720256","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5727775474","display_name":null,"funder_award_id":"MRSEC; NSF DMR 1720256","funder_id":"https://openalex.org/F4320333422","funder_display_name":"Materials Research Science and Engineering Center, Harvard University"},{"id":"https://openalex.org/G6265117655","display_name":null,"funder_award_id":"OAC-1925717","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6266480177","display_name":null,"funder_award_id":"MRSEC","funder_id":"https://openalex.org/F4320332500","funder_display_name":"University of California, Santa Barbara"},{"id":"https://openalex.org/G6512159266","display_name":null,"funder_award_id":"1720256","funder_id":"https://openalex.org/F4320333422","funder_display_name":"Materials Research Science and Engineering Center, Harvard University"},{"id":"https://openalex.org/G6912258823","display_name":null,"funder_award_id":"1720256","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7061003935","display_name":null,"funder_award_id":"NSF DMR 1720256","funder_id":"https://openalex.org/F4320337965","funder_display_name":"California NanoSystems Institute"},{"id":"https://openalex.org/G7437795455","display_name":null,"funder_award_id":"1720256","funder_id":"https://openalex.org/F4320332500","funder_display_name":"University of California, Santa Barbara"},{"id":"https://openalex.org/G7765571271","display_name":null,"funder_award_id":"MRSEC","funder_id":"https://openalex.org/F4320337367","funder_display_name":"Division of Materials Research"},{"id":"https://openalex.org/G8230913862","display_name":null,"funder_award_id":"NSF DMR 1720256","funder_id":"https://openalex.org/F4320337367","funder_display_name":"Division of Materials Research"},{"id":"https://openalex.org/G8708120587","display_name":null,"funder_award_id":"2124039","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8933114764","display_name":null,"funder_award_id":"NSF DMR 1720256","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"},{"id":"https://openalex.org/F4320332500","display_name":"University of California, Santa Barbara","ror":"https://ror.org/02t274463"},{"id":"https://openalex.org/F4320333422","display_name":"Materials Research Science and Engineering Center, Harvard University","ror":null},{"id":"https://openalex.org/F4320337367","display_name":"Division of Materials Research","ror":"https://ror.org/01pc7k308"},{"id":"https://openalex.org/F4320337965","display_name":"California NanoSystems Institute","ror":"https://ror.org/00q7fqf35"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4214686755.pdf","grobid_xml":"https://content.openalex.org/works/W4214686755.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W2000967104","https://openalex.org/W2009832130","https://openalex.org/W2044033049","https://openalex.org/W2048266589","https://openalex.org/W2053171205","https://openalex.org/W2067523571","https://openalex.org/W2094756095","https://openalex.org/W2125203716","https://openalex.org/W2152839228","https://openalex.org/W2178628967","https://openalex.org/W2483966489","https://openalex.org/W2518628311","https://openalex.org/W2605347906","https://openalex.org/W2606722458","https://openalex.org/W2883542588","https://openalex.org/W2883920103","https://openalex.org/W2886557986","https://openalex.org/W2891680100","https://openalex.org/W2949591530","https://openalex.org/W2963122961","https://openalex.org/W2963367920","https://openalex.org/W2963748441","https://openalex.org/W3001665736","https://openalex.org/W3017024317","https://openalex.org/W3024621361","https://openalex.org/W3037132819","https://openalex.org/W3096609285","https://openalex.org/W3099513244","https://openalex.org/W3131922516","https://openalex.org/W3159727696","https://openalex.org/W3189877953","https://openalex.org/W4238341497","https://openalex.org/W4239722617","https://openalex.org/W4245199738"],"related_works":["https://openalex.org/W4318718867","https://openalex.org/W4286758842","https://openalex.org/W121182129","https://openalex.org/W4319995060","https://openalex.org/W4293025825","https://openalex.org/W2392098988","https://openalex.org/W4221138841","https://openalex.org/W1517054283","https://openalex.org/W3130954105","https://openalex.org/W2905887716"],"abstract_inverted_index":{"Transformer":[0,24,54,81,101],"Neural":[1],"Networks":[2],"have":[3],"demonstrated":[4],"leading":[5],"performance":[6,119,132],"in":[7,64],"many":[8],"applications":[9],"spanning":[10],"over":[11,122,140],"language":[12],"understanding,":[13],"image":[14],"processing,":[15],"and":[16,33,86,130,134,142],"generative":[17],"modeling.":[18],"Despite":[19],"the":[20,50,58,80,104,117],"impressive":[21],"performance,":[22],"long-sequence":[23],"processing":[25],"is":[26],"expensive":[27],"due":[28],"to":[29,73,83],"quadratic":[30],"computation":[31],"complexity":[32],"memory":[34],"consumption":[35],"of":[36,52,114,120,136],"self-attention.":[37],"In":[38,125],"this":[39],"paper,":[40],"we":[41,71,93],"present":[42],"DOTA,":[43],"an":[44,65],"algorithm-architecture":[45],"co-design":[46],"that":[47,60],"effectively":[48],"addresses":[49],"challenges":[51],"scalable":[53],"inference.":[55],"Based":[56],"on":[57,110],"insight":[59],"not":[61],"all":[62],"connections":[63,89],"attention":[66,106],"graph":[67],"are":[68],"equally":[69],"important,":[70],"propose":[72],"jointly":[74],"optimize":[75],"a":[76,95,111],"lightweight":[77],"Detector":[78],"with":[79],"model":[82],"accurately":[84],"detect":[85],"omit":[87],"weak":[88],"during":[90],"runtime.":[91],"Furthermore,":[92],"design":[94],"specialized":[96],"system":[97],"architecture":[98],"for":[99],"end-to-end":[100],"acceleration":[102],"using":[103],"proposed":[105],"detection":[107],"mechanism.":[108],"Experiments":[109],"wide":[112],"range":[113],"benchmarks":[115],"demonstrate":[116],"superior":[118],"DOTA":[121,127],"other":[123],"solutions.":[124],"summary,":[126],"achieves":[128],"152.6x":[129],"4.5x":[131],"speedup":[133],"orders":[135],"magnitude":[137],"energy-efficiency":[138],"improvements":[139],"GPU":[141],"customized":[143],"hardware,":[144],"respectively.":[145]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":52},{"year":2024,"cited_by_count":33},{"year":2023,"cited_by_count":21},{"year":2022,"cited_by_count":2}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}
