{"id":"https://openalex.org/W4399487406","doi":"https://doi.org/10.1145/3649476.3658810","title":"Enhancing Long Sequence Input Processing in FPGA-Based Transformer Accelerators through Attention Fusion","display_name":"Enhancing Long Sequence Input Processing in FPGA-Based Transformer Accelerators through Attention Fusion","publication_year":2024,"publication_date":"2024-06-10","ids":{"openalex":"https://openalex.org/W4399487406","doi":"https://doi.org/10.1145/3649476.3658810"},"language":"en","primary_location":{"id":"doi:10.1145/3649476.3658810","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3649476.3658810","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Great Lakes Symposium on VLSI 2024","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/A5014908428","display_name":"Yunji Qin","orcid":"https://orcid.org/0009-0005-9404-581X"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunji Qin","raw_affiliation_strings":["School of Computer Science and Technology, University of Science and Technology of China, China"],"raw_orcid":"https://orcid.org/0009-0005-9404-581X","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034765006","display_name":"Wenqi Lou","orcid":"https://orcid.org/0000-0002-2240-6672"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenqi Lou","raw_affiliation_strings":["Software Engineering, University of Science and Technology of China, China"],"raw_orcid":"https://orcid.org/0000-0002-2240-6672","affiliations":[{"raw_affiliation_string":"Software Engineering, University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011884768","display_name":"Chao Wang","orcid":"https://orcid.org/0000-0002-9403-5575"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Wang","raw_affiliation_strings":["School of Computer Science and Technology, University of Science and Technology of China, China"],"raw_orcid":"https://orcid.org/0000-0002-9403-5575","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072915437","display_name":"Lei Gong","orcid":"https://orcid.org/0000-0002-8391-5526"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Gong","raw_affiliation_strings":["School of Computer Science and Technology, University of Science and Technology of China, China"],"raw_orcid":"https://orcid.org/0000-0002-8391-5526","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077322091","display_name":"Xuehai Zhou","orcid":"https://orcid.org/0000-0002-8360-3143"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuehai Zhou","raw_affiliation_strings":["School of Computer Science and Technology, University of Science and Technology of China, China"],"raw_orcid":"https://orcid.org/0000-0002-8360-3143","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":14.7215,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.99487313,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"599","last_page":"603"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10323","display_name":"Analog and Mixed-Signal Circuit Design","score":0.9926999807357788,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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/T10323","display_name":"Analog and Mixed-Signal Circuit Design","score":0.9926999807357788,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.9900000095367432,"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/T10468","display_name":"Photovoltaic System Optimization Techniques","score":0.989799976348877,"subfield":{"id":"https://openalex.org/subfields/2105","display_name":"Renewable Energy, Sustainability and the Environment"},"field":{"id":"https://openalex.org/fields/21","display_name":"Energy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.6979327201843262},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.6104042530059814},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6011489033699036},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5696017742156982},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.531062126159668},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42983436584472656},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3192177414894104},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.18505698442459106},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.18077781796455383},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.0786537230014801}],"concepts":[{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.6979327201843262},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.6104042530059814},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6011489033699036},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5696017742156982},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.531062126159668},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42983436584472656},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3192177414894104},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.18505698442459106},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.18077781796455383},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0786537230014801},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3649476.3658810","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3649476.3658810","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Great Lakes Symposium on VLSI 2024","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.46000000834465027,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[{"id":"https://openalex.org/G1313329494","display_name":null,"funder_award_id":"Y2021121","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"},{"id":"https://openalex.org/G1407914020","display_name":null,"funder_award_id":"62102383,61976200,62172380","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"},{"id":"https://openalex.org/G2122794702","display_name":null,"funder_award_id":"2022YFB4501600,2022YFB4501603","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"}],"funders":[{"id":"https://openalex.org/F4320323817","display_name":"Universitas Brawijaya","ror":"https://ror.org/01wk3d929"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W3047848469","https://openalex.org/W3130240120","https://openalex.org/W3155487259","https://openalex.org/W3159727696","https://openalex.org/W3198625877","https://openalex.org/W4214686755","https://openalex.org/W4286001027","https://openalex.org/W4291653336","https://openalex.org/W4293023328","https://openalex.org/W4308083526","https://openalex.org/W4308479898","https://openalex.org/W4318541578","https://openalex.org/W4379115894","https://openalex.org/W4388214800","https://openalex.org/W4389162698"],"related_works":["https://openalex.org/W2111241003","https://openalex.org/W4200391368","https://openalex.org/W2355315220","https://openalex.org/W2210979487","https://openalex.org/W2074043759","https://openalex.org/W2316202402","https://openalex.org/W2096844293","https://openalex.org/W2363944576","https://openalex.org/W2351041855","https://openalex.org/W2570254841"],"abstract_inverted_index":{"Attention-based":[0],"transformers":[1],"have":[2],"achieved":[3],"significant":[4],"performance":[5],"breakthroughs":[6],"in":[7,100],"natural":[8],"language":[9],"processing":[10],"(NLP)":[11],"and":[12,45,80,97,104,124],"computer":[13],"vision":[14],"(CV)":[15],"tasks.":[16],"Meanwhile,":[17],"the":[18,50,86,95,101,118],"ever-increasing":[19],"length":[20,150],"of":[21,49,131],"today\u2019s":[22],"input":[23,59,67,82,111,148],"sequences":[24],"puts":[25],"much":[26],"pressure":[27],"on":[28,117],"computing":[29],"devices.":[30],"FPGAs":[31],"are":[32,55],"widely":[33],"used":[34],"to":[35,40,57,64,90,108,146],"accelerate":[36,65],"Transformer":[37,53,76],"inference":[38],"due":[39],"their":[41],"high":[42],"energy":[43],"efficiency":[44,129],"flexibility.":[46],"However,":[47],"most":[48],"existing":[51],"FPGA-based":[52],"accelerators":[54],"oriented":[56],"small":[58],"lengths,":[60],"making":[61],"it":[62],"hard":[63],"long":[66],"sequences.":[68],"To":[69],"this":[70],"end,":[71],"we":[72],"design":[73],"an":[74],"efficient":[75],"accelerator":[77,107,142],"for":[78,122],"FPGA":[79,138],"long-sequence":[81],"scenarios.":[83],"We":[84,114],"use":[85,115],"tiling":[87],"softmax":[88],"algorithm":[89],"fuse":[91],"attention":[92,102],"computation,":[93],"eliminating":[94],"memory":[96],"bandwidth":[98],"bottleneck":[99],"layer":[103],"allowing":[105],"our":[106,125,141],"support":[109,144],"arbitrary":[110],"sequence":[112,149],"lengths.":[113],"BERT-Base":[116],"Alveo":[119],"U50":[120],"board":[121],"evaluation,":[123],"implementation":[126],"achieves":[127],"computational":[128],"improvements":[130],"1.09":[132],"\u223c":[133],"2.48":[134],"\u00d7":[135],"over":[136],"prior":[137],"accelerators.":[139],"Besides,":[140],"can":[143],"up":[145],"175K":[147],"when":[151],"running":[152],"BERT-like":[153],"structures,":[154],"far":[155],"more":[156],"than":[157],"previous":[158],"designs.":[159]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}