{"id":"https://openalex.org/W2889959382","doi":"https://doi.org/10.1145/3287624.3287717","title":"Implementing neural machine translation with bi-directional GRU and attention mechanism on FPGAs using HLS","display_name":"Implementing neural machine translation with bi-directional GRU and attention mechanism on FPGAs using HLS","publication_year":2019,"publication_date":"2019-01-18","ids":{"openalex":"https://openalex.org/W2889959382","doi":"https://doi.org/10.1145/3287624.3287717","mag":"2889959382"},"language":"en","primary_location":{"id":"doi:10.1145/3287624.3287717","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3287624.3287717","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th Asia and South Pacific Design Automation Conference","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/A5101584016","display_name":"Qin Li","orcid":"https://orcid.org/0000-0001-5220-9090"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qin Li","raw_affiliation_strings":["University of Illinois at Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100330729","display_name":"Xiaofan Zhang","orcid":"https://orcid.org/0000-0001-5081-3972"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaofan Zhang","raw_affiliation_strings":["University of Illinois at Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030156276","display_name":"Jinjun Xiong","orcid":"https://orcid.org/0000-0002-2620-4859"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"JinJun Xiong","raw_affiliation_strings":["IBM"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040404999","display_name":"Wen\u2010mei Hwu","orcid":"https://orcid.org/0000-0003-2532-5349"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wen-mei Hwu","raw_affiliation_strings":["University of Illinois at Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056321228","display_name":"Deming Chen","orcid":"https://orcid.org/0000-0002-3016-0270"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Deming Chen","raw_affiliation_strings":["University of Illinois at Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":33,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"693","last_page":"698"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9973000288009644,"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":0.9973000288009644,"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":0.9955000281333923,"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/T11032","display_name":"VLSI and Analog Circuit Testing","score":0.9835000038146973,"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":0.8544167876243591},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.7169884443283081},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.6504238843917847},{"id":"https://openalex.org/keywords/flops","display_name":"FLOPS","score":0.5219744443893433},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.451055645942688},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.4316747486591339},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.42401671409606934},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.4134077727794647},{"id":"https://openalex.org/keywords/design-space-exploration","display_name":"Design space exploration","score":0.4123207926750183},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.39196401834487915},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3574989438056946},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.323650598526001},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1971011757850647}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8544167876243591},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.7169884443283081},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.6504238843917847},{"id":"https://openalex.org/C3826847","wikidata":"https://www.wikidata.org/wiki/Q188768","display_name":"FLOPS","level":2,"score":0.5219744443893433},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.451055645942688},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.4316747486591339},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.42401671409606934},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.4134077727794647},{"id":"https://openalex.org/C2776221188","wikidata":"https://www.wikidata.org/wiki/Q21072556","display_name":"Design space exploration","level":2,"score":0.4123207926750183},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.39196401834487915},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3574989438056946},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.323650598526001},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1971011757850647},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3287624.3287717","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3287624.3287717","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th Asia and South Pacific Design Automation Conference","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8600000143051147,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320316786","display_name":"Center for Cognitive Computing Systems Research","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1753482797","https://openalex.org/W2131774270","https://openalex.org/W2133564696","https://openalex.org/W2157331557","https://openalex.org/W2159584133","https://openalex.org/W2294320930","https://openalex.org/W2585720638","https://openalex.org/W2585774018","https://openalex.org/W2588448445","https://openalex.org/W2762910930","https://openalex.org/W2789246071","https://openalex.org/W2899915146","https://openalex.org/W2949888546","https://openalex.org/W2962820060","https://openalex.org/W4245175284","https://openalex.org/W6679436768"],"related_works":["https://openalex.org/W4292794827","https://openalex.org/W4224939635","https://openalex.org/W4282568311","https://openalex.org/W4313484792","https://openalex.org/W2951473296","https://openalex.org/W2883928845","https://openalex.org/W4288420200","https://openalex.org/W4285346947","https://openalex.org/W4365793791","https://openalex.org/W3145095675"],"abstract_inverted_index":{"Neural":[0],"machine":[1],"translation":[2,19,45,60,71],"(NMT)":[3],"is":[4,202],"a":[5,84,92,149,183,205],"popular":[6],"topic":[7],"in":[8,144,167],"Natural":[9],"Language":[10],"Processing":[11],"which":[12,73,140],"uses":[13],"deep":[14],"neural":[15],"networks":[16],"(DNNs)":[17],"for":[18,54,76,87,104,122,188,196],"from":[20],"source":[21],"to":[22,48,117,133],"targeted":[23,198],"languages.":[24],"With":[25],"the":[26,49,89,96,124,135,164,168,172,177,190,197],"emerging":[27],"technologies,":[28],"such":[29],"as":[30],"bidirectional":[31],"Gated":[32],"Recurrent":[33],"Units":[34],"(GRU),":[35],"attention":[36],"mechanisms,":[37],"and":[38,69,109,129,158,170],"beam-search":[39],"algorithms,":[40],"NMT":[41,94,191],"can":[42],"deliver":[43],"improved":[44,105],"quality":[46,61],"compared":[47],"conventional":[50],"statistics-based":[51],"methods,":[52],"especially":[53],"translating":[55],"long":[56],"sentences.":[57],"However,":[58],"higher":[59,66],"means":[62],"more":[63],"complicated":[64],"models,":[65],"computation/memory":[67],"demands,":[68],"longer":[70],"time,":[72],"causes":[74],"difficulties":[75],"practical":[77],"use.":[78],"In":[79],"this":[80],"paper,":[81],"we":[82,147,181],"propose":[83,182],"design":[85,150,201],"methodology":[86],"implementing":[88],"inference":[90],"of":[91,176],"real-life":[93],"(with":[95],"problem":[97],"size":[98],"=":[99],"172":[100],"GFLOP)":[101],"on":[102,204],"FPGA":[103],"run":[106],"time":[107],"latency":[108],"energy":[110],"efficiency.":[111],"We":[112],"use":[113],"High-Level":[114],"Synthesis":[115],"(HLS)":[116],"build":[118],"high-performance":[119],"parameterized":[120],"IPs":[121,132],"handling":[123],"most":[125],"basic":[126],"operations":[127],"(multiply-accumulations)":[128],"construct":[130],"these":[131],"accelerate":[134],"matrix-vector":[136],"multiplication":[137],"(MVM)":[138],"kernels,":[139],"are":[141],"frequently":[142],"used":[143],"NMT.":[145],"Also,":[146],"perform":[148],"space":[151],"exploration":[152],"by":[153],"considering":[154],"both":[155],"computation":[156],"resources":[157],"memory":[159],"access":[160],"bandwidth":[161],"when":[162],"utilizing":[163],"hardware":[165],"parallelism":[166],"model":[169],"generate":[171],"best":[173],"parameter":[174],"configurations":[175],"proposed":[178],"IPs.":[179],"Accordingly,":[180],"novel":[184],"hybrid":[185],"parallel":[186],"structure":[187],"accelerating":[189],"with":[192,208],"affordable":[193],"resource":[194],"overhead":[195],"FPGA.":[199],"Our":[200],"demonstrated":[203],"Xilinx":[206],"VCU118":[207],"overall":[209],"performance":[210],"at":[211],"7.16":[212],"GFLOPS.":[213]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":11},{"year":2019,"cited_by_count":6}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}