{"id":"https://openalex.org/W4413278525","doi":"https://doi.org/10.1109/icfpt64416.2024.11113430","title":"Famous: Flexible Accelerator for the Attention Mechanism of Transformer on Ultrascale+ FPGAs","display_name":"Famous: Flexible Accelerator for the Attention Mechanism of Transformer on Ultrascale+ FPGAs","publication_year":2024,"publication_date":"2024-12-10","ids":{"openalex":"https://openalex.org/W4413278525","doi":"https://doi.org/10.1109/icfpt64416.2024.11113430"},"language":"en","primary_location":{"id":"doi:10.1109/icfpt64416.2024.11113430","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icfpt64416.2024.11113430","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Conference on Field Programmable Technology (ICFPT)","raw_type":"proceedings-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/A5051434549","display_name":"Ehsan Kabir","orcid":"https://orcid.org/0009-0009-3335-9419"},"institutions":[{"id":"https://openalex.org/I78715868","display_name":"University of Arkansas at Fayetteville","ror":"https://ror.org/05jbt9m15","country_code":"US","type":"education","lineage":["https://openalex.org/I78715868"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ehsan Kabir","raw_affiliation_strings":["University of Arkansas,Department of EECS,Fayetteville,North Carolina"],"affiliations":[{"raw_affiliation_string":"University of Arkansas,Department of EECS,Fayetteville,North Carolina","institution_ids":["https://openalex.org/I78715868"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101142826","display_name":"MD Arafat Kabir","orcid":null},"institutions":[{"id":"https://openalex.org/I78715868","display_name":"University of Arkansas at Fayetteville","ror":"https://ror.org/05jbt9m15","country_code":"US","type":"education","lineage":["https://openalex.org/I78715868"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Md. Arafat Kabir","raw_affiliation_strings":["University of Arkansas,Department of EECS,Fayetteville,North Carolina"],"affiliations":[{"raw_affiliation_string":"University of Arkansas,Department of EECS,Fayetteville,North Carolina","institution_ids":["https://openalex.org/I78715868"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014210633","display_name":"Austin Downey","orcid":"https://orcid.org/0000-0002-5524-2416"},"institutions":[{"id":"https://openalex.org/I155781252","display_name":"University of South Carolina","ror":"https://ror.org/02b6qw903","country_code":"US","type":"education","lineage":["https://openalex.org/I155781252"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Austin R.J. Downey","raw_affiliation_strings":["University of South Carolina,Department of ME,USA"],"affiliations":[{"raw_affiliation_string":"University of South Carolina,Department of ME,USA","institution_ids":["https://openalex.org/I155781252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001266986","display_name":"Jason D. Bakos","orcid":"https://orcid.org/0000-0002-0821-6258"},"institutions":[{"id":"https://openalex.org/I155781252","display_name":"University of South Carolina","ror":"https://ror.org/02b6qw903","country_code":"US","type":"education","lineage":["https://openalex.org/I155781252"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jason D. Bakos","raw_affiliation_strings":["University of South Carolina,Department of CSE,USA"],"affiliations":[{"raw_affiliation_string":"University of South Carolina,Department of CSE,USA","institution_ids":["https://openalex.org/I155781252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062434121","display_name":"David Andrews","orcid":"https://orcid.org/0000-0003-1464-7107"},"institutions":[{"id":"https://openalex.org/I78715868","display_name":"University of Arkansas at Fayetteville","ror":"https://ror.org/05jbt9m15","country_code":"US","type":"education","lineage":["https://openalex.org/I78715868"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Andrews","raw_affiliation_strings":["University of Arkansas,Department of EECS,Fayetteville,North Carolina"],"affiliations":[{"raw_affiliation_string":"University of Arkansas,Department of EECS,Fayetteville,North Carolina","institution_ids":["https://openalex.org/I78715868"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069173833","display_name":"Miaoqing Huang","orcid":"https://orcid.org/0000-0001-7376-3744"},"institutions":[{"id":"https://openalex.org/I78715868","display_name":"University of Arkansas at Fayetteville","ror":"https://ror.org/05jbt9m15","country_code":"US","type":"education","lineage":["https://openalex.org/I78715868"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Miaoqing Huang","raw_affiliation_strings":["University of Arkansas,Department of EECS,Fayetteville,North Carolina"],"affiliations":[{"raw_affiliation_string":"University of Arkansas,Department of EECS,Fayetteville,North Carolina","institution_ids":["https://openalex.org/I78715868"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5051434549"],"corresponding_institution_ids":["https://openalex.org/I78715868"],"apc_list":null,"apc_paid":null,"fwci":0.4439,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.66049536,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"2"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12510","display_name":"Magneto-Optical Properties and Applications","score":0.9362000226974487,"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/T12510","display_name":"Magneto-Optical Properties and Applications","score":0.9362000226974487,"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/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.9253000020980835,"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/T10369","display_name":"Advanced MEMS and NEMS Technologies","score":0.9114999771118164,"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/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.7048383355140686},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5234783887863159},{"id":"https://openalex.org/keywords/mechanism","display_name":"Mechanism (biology)","score":0.5164373517036438},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4569672644138336},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3203597366809845},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.14643174409866333},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13679900765419006},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.1275080442428589}],"concepts":[{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.7048383355140686},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5234783887863159},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.5164373517036438},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4569672644138336},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3203597366809845},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.14643174409866333},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13679900765419006},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.1275080442428589},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icfpt64416.2024.11113430","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icfpt64416.2024.11113430","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Conference on Field Programmable Technology (ICFPT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8299999833106995,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W2997106510","https://openalex.org/W3162542754","https://openalex.org/W3196923642","https://openalex.org/W4286001027","https://openalex.org/W4384947633","https://openalex.org/W4388214726"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2111241003","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2096844293","https://openalex.org/W2363944576","https://openalex.org/W2351041855","https://openalex.org/W2570254841"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"FAMOUS,":[3],"a":[4,85],"flexible":[5],"hardware":[6],"accelerator":[7],"for":[8,27],"dense":[9],"multi-head":[10],"attention":[11,92],"(MHA)":[12],"computation":[13],"of":[14,30,45,90,99],"Transformer":[15],"neural":[16],"networks":[17],"(TNNs)":[18],"on":[19,60,68,109],"field-programmable":[20],"gate":[21],"arrays":[22],"(FPGAs).":[23],"It":[24,137],"is":[25,66,114,138],"optimized":[26],"high":[28],"utilization":[29],"processing":[31],"elements":[32],"and":[33,39,54,96,106,119,132],"on-chip":[34],"memories":[35],"to":[36,51],"improve":[37],"parallelism":[38],"reduce":[40],"latency.":[41],"An":[42],"efficient":[43],"tiling":[44],"large":[46],"matrices":[47],"has":[48],"been":[49],"employed":[50],"distribute":[52],"memory":[53],"computing":[55],"resources":[56],"across":[57],"different":[58],"modules":[59],"various":[61],"FPGA":[62],"platforms.":[63],"The":[64],"design":[65],"evaluated":[67],"Xilinx":[69],"Alveo":[70],"U55C":[71],"data":[72],"center":[73],"cards":[74],"containing":[75],"Ultrascale+":[76],"FPGAs.":[77],"Experimental":[78],"results":[79],"showed":[80],"that":[81],"it":[82,113],"can":[83],"attain":[84],"maximum":[86],"throughput,":[87],"the":[88,110,126,147],"number":[89],"parallel":[91],"heads,":[93],"embedding":[94],"dimension,":[95],"tile":[97],"size":[98],"328":[100],"(giga":[101],"operations/second":[102],"(GOPS)),":[103],"8,":[104],"768":[105],"64":[107],"respectively":[108],"U55C.":[111],"Furthermore,":[112],"<tex":[115,120,140],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[116,121,141],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$3.28":[117],"\\times$</tex>":[118,123,144],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$2.6":[122],"faster":[124,145],"than":[125,146],"Intel":[127],"Xeon":[128],"Gold":[129],"5220R":[130],"CPU":[131],"NVIDIA":[133],"V100":[134],"GPU":[135],"respectively.":[136],"also":[139],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$\\text{1.":[142],"3}":[143],"fastest":[148],"state-of-the-art":[149],"FPGA-based":[150],"accelerator.":[151]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}