{"id":"https://openalex.org/W2527036487","doi":"https://doi.org/10.1109/fpl.2016.7577314","title":"Accelerating recurrent neural networks in analytics servers: Comparison of FPGA, CPU, GPU, and ASIC","display_name":"Accelerating recurrent neural networks in analytics servers: Comparison of FPGA, CPU, GPU, and ASIC","publication_year":2016,"publication_date":"2016-08-01","ids":{"openalex":"https://openalex.org/W2527036487","doi":"https://doi.org/10.1109/fpl.2016.7577314","mag":"2527036487"},"language":"en","primary_location":{"id":"doi:10.1109/fpl.2016.7577314","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fpl.2016.7577314","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 26th International Conference on Field Programmable Logic and Applications (FPL)","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/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":true,"raw_author_name":"Eriko Nurvitadhi","raw_affiliation_strings":["Intel Corporation"],"affiliations":[{"raw_affiliation_string":"Intel Corporation","institution_ids":["https://openalex.org/I4210158342"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004251886","display_name":"Jaewoong Sim","orcid":"https://orcid.org/0000-0002-0403-9928"},"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":"Jaewoong Sim","raw_affiliation_strings":["Intel Corporation"],"affiliations":[{"raw_affiliation_string":"Intel Corporation","institution_ids":["https://openalex.org/I4210158342"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063801377","display_name":"David Sheffield","orcid":null},"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":"David Sheffield","raw_affiliation_strings":["Intel Corporation"],"affiliations":[{"raw_affiliation_string":"Intel Corporation","institution_ids":["https://openalex.org/I4210158342"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101912070","display_name":"Asit Mishra","orcid":"https://orcid.org/0000-0001-6489-6895"},"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":"Asit Mishra","raw_affiliation_strings":["Intel Corporation"],"affiliations":[{"raw_affiliation_string":"Intel Corporation","institution_ids":["https://openalex.org/I4210158342"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058825852","display_name":"Srivatsan Krishnan","orcid":"https://orcid.org/0000-0002-7148-5389"},"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":"Srivatsan Krishnan","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/A5110600508","display_name":"Debbie Marr","orcid":null},"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":"Debbie Marr","raw_affiliation_strings":["Intel Corporation"],"affiliations":[{"raw_affiliation_string":"Intel Corporation","institution_ids":["https://openalex.org/I4210158342"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5084078152"],"corresponding_institution_ids":["https://openalex.org/I4210158342"],"apc_list":null,"apc_paid":null,"fwci":20.1585,"has_fulltext":false,"cited_by_count":174,"citation_normalized_percentile":{"value":0.9970872,"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":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.998199999332428,"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"}},"topics":[{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.998199999332428,"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"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9972000122070312,"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/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.9882000088691711,"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/application-specific-integrated-circuit","display_name":"Application-specific integrated circuit","score":0.8465271592140198},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8063449859619141},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.7342953681945801},{"id":"https://openalex.org/keywords/coprocessor","display_name":"Coprocessor","score":0.5195255875587463},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4969034492969513},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.46069997549057007},{"id":"https://openalex.org/keywords/central-processing-unit","display_name":"Central processing unit","score":0.41625383496284485},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3744010627269745},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.3503262996673584},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.33945566415786743},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2957969307899475},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.26383864879608154}],"concepts":[{"id":"https://openalex.org/C77390884","wikidata":"https://www.wikidata.org/wiki/Q217302","display_name":"Application-specific integrated circuit","level":2,"score":0.8465271592140198},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8063449859619141},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.7342953681945801},{"id":"https://openalex.org/C86111242","wikidata":"https://www.wikidata.org/wiki/Q859595","display_name":"Coprocessor","level":2,"score":0.5195255875587463},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4969034492969513},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.46069997549057007},{"id":"https://openalex.org/C49154492","wikidata":"https://www.wikidata.org/wiki/Q5300","display_name":"Central processing unit","level":2,"score":0.41625383496284485},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3744010627269745},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.3503262996673584},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.33945566415786743},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2957969307899475},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.26383864879608154}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/fpl.2016.7577314","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fpl.2016.7577314","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 26th International Conference on Field Programmable Logic and Applications (FPL)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5299999713897705,"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":17,"referenced_works":["https://openalex.org/W179875071","https://openalex.org/W1492347181","https://openalex.org/W1924770834","https://openalex.org/W1990315422","https://openalex.org/W2145431022","https://openalex.org/W2153579005","https://openalex.org/W2157331557","https://openalex.org/W2177436562","https://openalex.org/W2193413348","https://openalex.org/W2351401301","https://openalex.org/W2949640717","https://openalex.org/W2964033223","https://openalex.org/W4294170691","https://openalex.org/W6640212811","https://openalex.org/W6682691769","https://openalex.org/W6685823913","https://openalex.org/W6687566353"],"related_works":["https://openalex.org/W2137567370","https://openalex.org/W1988690899","https://openalex.org/W1485756991","https://openalex.org/W2376218453","https://openalex.org/W2984236338","https://openalex.org/W2609406488","https://openalex.org/W2503163466","https://openalex.org/W2271965480","https://openalex.org/W2154903817","https://openalex.org/W1541877257"],"abstract_inverted_index":{"Recurrent":[0,25],"neural":[1],"networks":[2],"(RNNs)":[3],"provide":[4],"state-of-the-art":[5,21],"accuracy":[6],"for":[7,96],"performing":[8],"analytics":[9],"on":[10],"datasets":[11],"with":[12,111],"sequence":[13],"(e.g.,":[14],"language":[15],"model).":[16],"This":[17],"paper":[18],"studied":[19],"a":[20],"RNN":[22],"variant,":[23],"Gated":[24],"Unit":[26],"(GRU).":[27],"We":[28],"first":[29],"proposed":[30],"memoization":[31],"optimization":[32],"to":[33,59,68,122],"avoid":[34],"3":[35],"out":[36],"of":[37,49],"the":[38,47,50,57,61,120,124],"6":[39],"dense":[40],"matrix":[41],"vector":[42],"multiplications":[43],"(SGEMVs)":[44],"that":[45,77],"are":[46],"majority":[48],"computation":[51],"in":[52,66],"GRU.":[53,107],"Then,":[54],"we":[55],"study":[56],"opportunities":[58],"accelerate":[60],"remaining":[62],"SGEMVs":[63],"using":[64],"FPGAs,":[65],"comparison":[67],"14-nm":[69],"ASIC,":[70],"GPU,":[71],"and":[72,84,92,116],"multi-core":[73],"CPU.":[74],"Results":[75],"show":[76],"FPGA":[78],"provides":[79],"superior":[80],"performance/Watt":[81],"over":[82],"CPU":[83],"GPU":[85],"because":[86],"FPGA's":[87],"on-chip":[88,114],"BRAMs,":[89,115],"hard":[90],"DSPs,":[91,113],"reconfigurable":[93],"fabric":[94],"allow":[95],"efficiently":[97],"extracting":[98],"fine-grained":[99],"parallelisms":[100],"from":[101],"small/medium":[102],"size":[103],"matrices":[104],"used":[105],"by":[106],"Moreover,":[108],"newer":[109],"FPGAs":[110],"more":[112],"higher":[117],"frequency":[118],"have":[119],"potential":[121],"narrow":[123],"FPGA-ASIC":[125],"efficiency":[126],"gap.":[127]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":14},{"year":2022,"cited_by_count":30},{"year":2021,"cited_by_count":23},{"year":2020,"cited_by_count":26},{"year":2019,"cited_by_count":27},{"year":2018,"cited_by_count":23},{"year":2017,"cited_by_count":11},{"year":2016,"cited_by_count":2}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}