{"id":"https://openalex.org/W3160207692","doi":"https://doi.org/10.1109/icfpt51103.2020.00012","title":"A Reconfigurable Multithreaded Accelerator for Recurrent Neural Networks","display_name":"A Reconfigurable Multithreaded Accelerator for Recurrent Neural Networks","publication_year":2020,"publication_date":"2020-12-01","ids":{"openalex":"https://openalex.org/W3160207692","doi":"https://doi.org/10.1109/icfpt51103.2020.00012","mag":"3160207692"},"language":"en","primary_location":{"id":"doi:10.1109/icfpt51103.2020.00012","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icfpt51103.2020.00012","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 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/A5054475218","display_name":"Zhiqiang Que","orcid":"https://orcid.org/0000-0002-9263-6529"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Zhiqiang Que","raw_affiliation_strings":["Imperial College London, UK"],"affiliations":[{"raw_affiliation_string":"Imperial College London, UK","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070734898","display_name":"Hiroki Nakahara","orcid":"https://orcid.org/0000-0002-5701-7466"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroki Nakahara","raw_affiliation_strings":["Tokyo Institute of Technology, Japan"],"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057043409","display_name":"Hongxiang Fan","orcid":"https://orcid.org/0000-0003-2387-5611"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Hongxiang Fan","raw_affiliation_strings":["Imperial College London, UK"],"affiliations":[{"raw_affiliation_string":"Imperial College London, UK","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010981284","display_name":"Jiuxi Meng","orcid":"https://orcid.org/0000-0001-9261-2300"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jiuxi Meng","raw_affiliation_strings":["Imperial College London, UK"],"affiliations":[{"raw_affiliation_string":"Imperial College London, UK","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009397115","display_name":"Kuen Hung Tsoi","orcid":"https://orcid.org/0000-0002-6856-6727"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kuen Hung Tsoi","raw_affiliation_strings":["Corerain Technologies Ltd., China"],"affiliations":[{"raw_affiliation_string":"Corerain Technologies Ltd., China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103060695","display_name":"Xinyu Niu","orcid":"https://orcid.org/0000-0003-0202-9408"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xinyu Niu","raw_affiliation_strings":["Corerain Technologies Ltd., China"],"affiliations":[{"raw_affiliation_string":"Corerain Technologies Ltd., China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084078152","display_name":"Eriko Nurvitadhi","orcid":"https://orcid.org/0000-0002-2347-9590"},"institutions":[{"id":"https://openalex.org/I4210158342","display_name":"Intel (United Kingdom)","ror":"https://ror.org/058cxws58","country_code":"GB","type":"company","lineage":["https://openalex.org/I1343180700","https://openalex.org/I4210158342"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Eriko Nurvitadhi","raw_affiliation_strings":["Intel Corporation"],"affiliations":[{"raw_affiliation_string":"Intel Corporation","institution_ids":["https://openalex.org/I4210158342"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057940557","display_name":"Wayne Luk","orcid":"https://orcid.org/0000-0002-6750-927X"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Wayne Luk","raw_affiliation_strings":["Imperial College London, UK"],"affiliations":[{"raw_affiliation_string":"Imperial College London, UK","institution_ids":["https://openalex.org/I47508984"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5054475218"],"corresponding_institution_ids":["https://openalex.org/I47508984"],"apc_list":null,"apc_paid":null,"fwci":0.6839,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.72973382,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"20","last_page":"28"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":1.0,"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":1.0,"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/T11714","display_name":"Multimodal Machine Learning 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":0.9991000294685364,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8694800138473511},{"id":"https://openalex.org/keywords/stratix","display_name":"Stratix","score":0.7626112699508667},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.6858382821083069},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.6825082302093506},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.5315845608711243},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.475950688123703},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.44035834074020386},{"id":"https://openalex.org/keywords/lookup-table","display_name":"Lookup table","score":0.4391229450702667},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4049665331840515},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.36658596992492676},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.36523622274398804},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3523160517215729},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.29313331842422485},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.11441263556480408}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8694800138473511},{"id":"https://openalex.org/C2776277307","wikidata":"https://www.wikidata.org/wiki/Q22074755","display_name":"Stratix","level":3,"score":0.7626112699508667},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.6858382821083069},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.6825082302093506},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.5315845608711243},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.475950688123703},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.44035834074020386},{"id":"https://openalex.org/C134835016","wikidata":"https://www.wikidata.org/wiki/Q690265","display_name":"Lookup table","level":2,"score":0.4391229450702667},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4049665331840515},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.36658596992492676},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.36523622274398804},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3523160517215729},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29313331842422485},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.11441263556480408},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icfpt51103.2020.00012","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icfpt51103.2020.00012","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Conference on Field-Programmable Technology (ICFPT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","score":0.8700000047683716,"display_name":"Affordable and clean energy"}],"awards":[{"id":"https://openalex.org/G1826932366","display_name":null,"funder_award_id":"EP/L016796/1,EP/N031768/1,EP/P010040/1,EP/S030069/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G4587427570","display_name":null,"funder_award_id":"EP/S030069/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G7493804148","display_name":null,"funder_award_id":"EP/N031768/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G774180880","display_name":null,"funder_award_id":"EP/P010040/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320307102","display_name":"Intel Corporation","ror":"https://ror.org/01ek73717"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":63,"referenced_works":["https://openalex.org/W1895577753","https://openalex.org/W1922655562","https://openalex.org/W1923404803","https://openalex.org/W1947481528","https://openalex.org/W1995140396","https://openalex.org/W2043735637","https://openalex.org/W2052839611","https://openalex.org/W2064675550","https://openalex.org/W2113459411","https://openalex.org/W2177436562","https://openalex.org/W2193413348","https://openalex.org/W2527036487","https://openalex.org/W2585720638","https://openalex.org/W2588448445","https://openalex.org/W2606722458","https://openalex.org/W2626211758","https://openalex.org/W2727238169","https://openalex.org/W2732358839","https://openalex.org/W2786827964","https://openalex.org/W2788838111","https://openalex.org/W2798291715","https://openalex.org/W2827334269","https://openalex.org/W2883929540","https://openalex.org/W2898970087","https://openalex.org/W2901663942","https://openalex.org/W2903735800","https://openalex.org/W2904773682","https://openalex.org/W2915106038","https://openalex.org/W2946610455","https://openalex.org/W2948244774","https://openalex.org/W2949084706","https://openalex.org/W2949660525","https://openalex.org/W2950533501","https://openalex.org/W2951183276","https://openalex.org/W2960979574","https://openalex.org/W2962820060","https://openalex.org/W2963042536","https://openalex.org/W2963511748","https://openalex.org/W2964008850","https://openalex.org/W2964033223","https://openalex.org/W2971507840","https://openalex.org/W2976697034","https://openalex.org/W2986441544","https://openalex.org/W2990772310","https://openalex.org/W3003168380","https://openalex.org/W3004246420","https://openalex.org/W3008515469","https://openalex.org/W3016939927","https://openalex.org/W3034833480","https://openalex.org/W3037822942","https://openalex.org/W3040903763","https://openalex.org/W3043406639","https://openalex.org/W3047750904","https://openalex.org/W3048034223","https://openalex.org/W3089019106","https://openalex.org/W3090325485","https://openalex.org/W3092379737","https://openalex.org/W3106543020","https://openalex.org/W4287663079","https://openalex.org/W6676984168","https://openalex.org/W6687566353","https://openalex.org/W6747593890","https://openalex.org/W6784648519"],"related_works":["https://openalex.org/W1509155667","https://openalex.org/W2518118925","https://openalex.org/W2024574431","https://openalex.org/W2117300767","https://openalex.org/W3208151864","https://openalex.org/W2374017528","https://openalex.org/W4285503609","https://openalex.org/W2126248441","https://openalex.org/W2306407715","https://openalex.org/W1564576805"],"abstract_inverted_index":{"Recurrent":[0],"Neural":[1],"Network":[2],"(RNN)":[3],"is":[4,25,72,101,164],"a":[5,38,64,127,142,146],"key":[6],"technology":[7],"for":[8,22,44],"sequential":[9],"applications":[10],"which":[11,74,174],"require":[12],"efficient":[13,20],"and":[14,32,51,119,168],"realtime":[15],"implementations.":[16],"Despite":[17],"its":[18,29],"popularity,":[19],"acceleration":[21],"RNN":[23],"inference":[24,186],"challenging":[26],"due":[27],"to":[28,47,115,180],"recurrent":[30],"nature":[31],"data":[33,84],"dependencies.":[34],"This":[35],"paper":[36],"proposes":[37],"multi-threaded":[39,67],"neural":[40],"processing":[41,49],"unit":[42],"(NPU)":[43],"RNN/LSTM":[45],"inferences":[46],"increase":[48,116],"abilities":[50],"quality":[52],"of":[53,55,93,113],"service":[54],"cloud-based":[56],"NPUs":[57,88],"by":[58],"improving":[59],"their":[60],"hardware":[61,70,117,162],"utilization.":[62],"Besides,":[63],"custom":[65],"coarse-grained":[66],"LSTM":[68,80],"(CGMT-LSTM)":[69],"architecture":[71,163],"introduced,":[73],"switches":[75],"tasks":[76],"among":[77],"threads":[78],"when":[79],"computational":[81],"kernels":[82],"meet":[83],"hazard.":[85],"These":[86,108],"logical":[87,99],"share":[89],"nearly":[90],"all":[91],"resources":[92],"the":[94,111,156],"physical":[95],"NPU.":[96],"When":[97,150],"one":[98,104,144],"NPU":[100,130],"stalled,":[102],"another":[103],"can":[105],"make":[106],"progress.":[107],"optimizations":[109],"improve":[110],"exploitation":[112],"parallelism":[114],"utilization":[118],"enhance":[120],"system":[121],"throughput.":[122],"Evaluation":[123],"results":[124],"show":[125],"that":[126,176],"dual-threaded":[128],"CGMT-LSTM":[129],"gains":[131],"27%":[132],"more":[133,139],"performance":[134,182],"while":[135],"only":[136],"has":[137],"3.8%":[138],"area":[140],"than":[141],"single-threaded":[143],"using":[145],"Stratix":[147],"10":[148],"FPGA.":[149],"compared":[151],"with":[152],"an":[153],"implementation":[154],"on":[155],"Tesla":[157],"V100":[158],"GPU,":[159],"our":[160,177],"novel":[161],"6.62":[165],"times":[166,170],"faster":[167],"15.88":[169],"higher":[171],"power":[172],"efficiency,":[173],"demonstrates":[175],"approach":[178],"contributes":[179],"high":[181],"energy-efficient":[183],"FPGA-based":[184],"multi-LSTM":[185],"systems.":[187]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}