{"id":"https://openalex.org/W4312964950","doi":"https://doi.org/10.1109/iscas48785.2022.9937531","title":"A Resource-Saving Energy-Efficient Reconfigurable Hardware Accelerator for BERT-based Deep Neural Network Language Models using FFT Multiplication","display_name":"A Resource-Saving Energy-Efficient Reconfigurable Hardware Accelerator for BERT-based Deep Neural Network Language Models using FFT Multiplication","publication_year":2022,"publication_date":"2022-05-28","ids":{"openalex":"https://openalex.org/W4312964950","doi":"https://doi.org/10.1109/iscas48785.2022.9937531"},"language":"en","primary_location":{"id":"doi:10.1109/iscas48785.2022.9937531","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscas48785.2022.9937531","pdf_url":null,"source":{"id":"https://openalex.org/S4363604393","display_name":"2022 IEEE International Symposium on Circuits and Systems (ISCAS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Symposium on Circuits and Systems (ISCAS)","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/A5035738930","display_name":"Rodrigue Rizk","orcid":"https://orcid.org/0000-0002-4392-4188"},"institutions":[{"id":"https://openalex.org/I79516672","display_name":"University of Louisiana at Lafayette","ror":"https://ror.org/01x8rc503","country_code":"US","type":"education","lineage":["https://openalex.org/I2799628689","https://openalex.org/I79516672"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Rodrigue Rizk","raw_affiliation_strings":["University of Louisiana at Lafayette,The Center for Advanced Computer Studies,Louisiana,USA","The Center for Advanced Computer Studies, University of Louisiana at Lafayette, Louisiana, USA"],"affiliations":[{"raw_affiliation_string":"University of Louisiana at Lafayette,The Center for Advanced Computer Studies,Louisiana,USA","institution_ids":["https://openalex.org/I79516672"]},{"raw_affiliation_string":"The Center for Advanced Computer Studies, University of Louisiana at Lafayette, Louisiana, USA","institution_ids":["https://openalex.org/I79516672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067083454","display_name":"Dominick Rizk","orcid":"https://orcid.org/0000-0001-8078-4420"},"institutions":[{"id":"https://openalex.org/I79516672","display_name":"University of Louisiana at Lafayette","ror":"https://ror.org/01x8rc503","country_code":"US","type":"education","lineage":["https://openalex.org/I2799628689","https://openalex.org/I79516672"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dominick Rizk","raw_affiliation_strings":["University of Louisiana at Lafayette,The Center for Advanced Computer Studies,Louisiana,USA","The Center for Advanced Computer Studies, University of Louisiana at Lafayette, Louisiana, USA"],"affiliations":[{"raw_affiliation_string":"University of Louisiana at Lafayette,The Center for Advanced Computer Studies,Louisiana,USA","institution_ids":["https://openalex.org/I79516672"]},{"raw_affiliation_string":"The Center for Advanced Computer Studies, University of Louisiana at Lafayette, Louisiana, USA","institution_ids":["https://openalex.org/I79516672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062755022","display_name":"Frederic Rizk","orcid":"https://orcid.org/0000-0001-7443-7254"},"institutions":[{"id":"https://openalex.org/I79516672","display_name":"University of Louisiana at Lafayette","ror":"https://ror.org/01x8rc503","country_code":"US","type":"education","lineage":["https://openalex.org/I2799628689","https://openalex.org/I79516672"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Frederic Rizk","raw_affiliation_strings":["University of Louisiana at Lafayette,The Center for Advanced Computer Studies,Louisiana,USA","The Center for Advanced Computer Studies, University of Louisiana at Lafayette, Louisiana, USA"],"affiliations":[{"raw_affiliation_string":"University of Louisiana at Lafayette,The Center for Advanced Computer Studies,Louisiana,USA","institution_ids":["https://openalex.org/I79516672"]},{"raw_affiliation_string":"The Center for Advanced Computer Studies, University of Louisiana at Lafayette, Louisiana, USA","institution_ids":["https://openalex.org/I79516672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101981174","display_name":"Ashok Kumar","orcid":"https://orcid.org/0000-0002-9740-1219"},"institutions":[{"id":"https://openalex.org/I79516672","display_name":"University of Louisiana at Lafayette","ror":"https://ror.org/01x8rc503","country_code":"US","type":"education","lineage":["https://openalex.org/I2799628689","https://openalex.org/I79516672"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ashok Kumar","raw_affiliation_strings":["University of Louisiana at Lafayette,The Center for Advanced Computer Studies,Louisiana,USA","The Center for Advanced Computer Studies, University of Louisiana at Lafayette, Louisiana, USA"],"affiliations":[{"raw_affiliation_string":"University of Louisiana at Lafayette,The Center for Advanced Computer Studies,Louisiana,USA","institution_ids":["https://openalex.org/I79516672"]},{"raw_affiliation_string":"The Center for Advanced Computer Studies, University of Louisiana at Lafayette, Louisiana, USA","institution_ids":["https://openalex.org/I79516672"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010023744","display_name":"Magdy Bayoumi","orcid":"https://orcid.org/0000-0002-0630-5273"},"institutions":[{"id":"https://openalex.org/I79516672","display_name":"University of Louisiana at Lafayette","ror":"https://ror.org/01x8rc503","country_code":"US","type":"education","lineage":["https://openalex.org/I2799628689","https://openalex.org/I79516672"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Magdy Bayoumi","raw_affiliation_strings":["University of Louisiana at Lafayette,The Center for Advanced Computer Studies,Louisiana,USA","The Center for Advanced Computer Studies, University of Louisiana at Lafayette, Louisiana, USA"],"affiliations":[{"raw_affiliation_string":"University of Louisiana at Lafayette,The Center for Advanced Computer Studies,Louisiana,USA","institution_ids":["https://openalex.org/I79516672"]},{"raw_affiliation_string":"The Center for Advanced Computer Studies, University of Louisiana at Lafayette, Louisiana, USA","institution_ids":["https://openalex.org/I79516672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5035738930"],"corresponding_institution_ids":["https://openalex.org/I79516672"],"apc_list":null,"apc_paid":null,"fwci":3.2189,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.94390044,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1675","last_page":"1679"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.9998999834060669,"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/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.9998999834060669,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9995999932289124,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9987000226974487,"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":0.8228840827941895},{"id":"https://openalex.org/keywords/hardware-acceleration","display_name":"Hardware acceleration","score":0.6198814511299133},{"id":"https://openalex.org/keywords/efficient-energy-use","display_name":"Efficient energy use","score":0.5617130994796753},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4593115448951721},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.45043396949768066},{"id":"https://openalex.org/keywords/high-level-synthesis","display_name":"High-level synthesis","score":0.42382174730300903},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.42210841178894043},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.39843159914016724},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3832246661186218},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.38060539960861206},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.3664062023162842},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.36044397950172424},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2098310887813568},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.08910447359085083}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8228840827941895},{"id":"https://openalex.org/C13164978","wikidata":"https://www.wikidata.org/wiki/Q600158","display_name":"Hardware acceleration","level":3,"score":0.6198814511299133},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.5617130994796753},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4593115448951721},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.45043396949768066},{"id":"https://openalex.org/C58013763","wikidata":"https://www.wikidata.org/wiki/Q5754574","display_name":"High-level synthesis","level":3,"score":0.42382174730300903},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.42210841178894043},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.39843159914016724},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3832246661186218},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.38060539960861206},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3664062023162842},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.36044397950172424},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2098310887813568},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.08910447359085083},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscas48785.2022.9937531","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscas48785.2022.9937531","pdf_url":null,"source":{"id":"https://openalex.org/S4363604393","display_name":"2022 IEEE International Symposium on Circuits and Systems (ISCAS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Symposium on Circuits and Systems (ISCAS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.6499999761581421}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1689711448","https://openalex.org/W1924770834","https://openalex.org/W2016589492","https://openalex.org/W2064675550","https://openalex.org/W2113459411","https://openalex.org/W2136848157","https://openalex.org/W2162953669","https://openalex.org/W2751366252","https://openalex.org/W2896457183","https://openalex.org/W2923014074","https://openalex.org/W2942764887","https://openalex.org/W2965373594","https://openalex.org/W2978017171","https://openalex.org/W3047848469","https://openalex.org/W3104393472","https://openalex.org/W3158872624","https://openalex.org/W3159911742","https://openalex.org/W3159958343","https://openalex.org/W3162542754","https://openalex.org/W3184454880","https://openalex.org/W4385245566","https://openalex.org/W6640212811","https://openalex.org/W6676984168","https://openalex.org/W6739901393","https://openalex.org/W6750615492","https://openalex.org/W6755207826","https://openalex.org/W6766673545","https://openalex.org/W6768851824","https://openalex.org/W6780226713"],"related_works":["https://openalex.org/W2392571380","https://openalex.org/W2392153588","https://openalex.org/W2995926156","https://openalex.org/W1919071401","https://openalex.org/W2996827035","https://openalex.org/W1732210391","https://openalex.org/W4295855328","https://openalex.org/W4205290991","https://openalex.org/W3147787617","https://openalex.org/W3158118579"],"abstract_inverted_index":{"Bidirectional":[0],"Encoder":[1],"Representations":[2],"from":[3],"Transformers":[4],"(BERT)":[5],"based":[6],"language":[7,45,128],"models":[8],"are":[9,251],"a":[10,24,60,79,89,113,119,161],"new":[11],"class":[12],"of":[13,104,118,176],"deep":[14,125],"neural":[15,31,126],"networks":[16,32],"with":[17,88],"an":[18],"attention":[19],"mechanism.":[20],"They":[21,37],"emerge":[22],"as":[23],"better":[25,34],"alternative":[26],"to":[27,111,172,206,212,224],"the":[28,102,109,174,177,181,190],"traditional":[29],"recurrent":[30],"for":[33,63,85,123,141,150,168,239],"sequence":[35],"representation.":[36],"have":[38],"achieved":[39],"state-of-the-art":[40,162],"performance":[41],"in":[42,226],"various":[43],"natural":[44],"processing":[46],"(NLP)":[47],"tasks.":[48],"Nevertheless,":[49],"they":[50],"demand":[51],"intensive":[52],"computation,":[53],"energy,":[54],"and":[55,69,96,116,201,210,219,231,248],"memory":[56],"requirements":[57],"which":[58],"pose":[59],"major":[61],"challenge":[62],"their":[64],"deployment":[65],"on":[66,138,155,180,242],"resource-constrained":[67,243],"platforms":[68,244],"edge":[70],"devices.":[71],"To":[72,101],"mitigate":[73],"these":[74],"limitations,":[75],"this":[76],"paper":[77],"proposes":[78],"novel":[80],"hardware":[81,98,121,192],"accelerator":[82,122,193],"design":[83,115,132,236],"dedicated":[84],"BERT-based":[86,124,152],"architectures":[87],"reconfigurable":[90,120],"functionality":[91],"that":[92,189],"improves":[93],"circuit":[94],"reusability":[95],"reduces":[97],"resources":[99],"utilization.":[100],"best":[103],"our":[105],"knowledge,":[106],"it":[107],"is":[108,148,165,237],"first":[110],"present":[112],"holistic":[114],"implementation":[117],"network":[127],"models.":[129],"The":[130],"proposed":[131,191],"leverages":[133],"Fast":[134],"Fourier":[135],"Transform-based":[136],"multiplication":[137],"block-circulant":[139],"matrices":[140],"accelerating":[142],"BERT":[143],"weights":[144],"matrices'":[145],"multiplication.":[146],"It":[147,164],"evaluated":[149,167],"different":[151],"model":[153],"configurations":[154],"mainstream":[156],"popular":[157],"benchmarks":[158],"while":[159],"achieving":[160],"performance.":[163],"also":[166],"distinct":[169],"batch":[170,178],"sizes":[171],"study":[173],"impact":[175],"size":[179],"energy":[182,232],"efficiency.":[183],"A":[184],"cross-platform":[185],"comparative":[186],"analysis":[187],"shows":[188],"achieves":[194],"$6":[195],"\\times,":[196,198,214],"27":[197],"3.18":[199],"\\times$,":[200,216,218],"$8":[202],"\\times$":[203,221],"improvement":[204,222],"compared":[205,223],"$C":[207],"P":[208],"U$,":[209],"up":[211],"$1.17":[213],"1.77":[215],"$5":[217],"$86":[220],"GPU":[225],"latency,":[227],"throughput,":[228],"power":[229],"consumption,":[230],"efficiency,":[233],"respectively.":[234],"This":[235],"suitable":[238],"efficient":[240],"NLP":[241],"where":[245],"low":[246],"latency":[247],"high":[249],"throughput":[250],"critical.":[252]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}