{"id":"https://openalex.org/W3130240120","doi":"https://doi.org/10.1145/3431920.3439477","title":"NPE: An FPGA-based Overlay Processor for Natural Language Processing","display_name":"NPE: An FPGA-based Overlay Processor for Natural Language Processing","publication_year":2021,"publication_date":"2021-02-17","ids":{"openalex":"https://openalex.org/W3130240120","doi":"https://doi.org/10.1145/3431920.3439477","mag":"3130240120"},"language":"en","primary_location":{"id":"doi:10.1145/3431920.3439477","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3431920.3439477","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 2021 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2104.06535","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Hamza Khan","orcid":null},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Hamza Khan","raw_affiliation_strings":["University of California, Los Angeles, Los Angeles, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California, Los Angeles, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Asma Khan","orcid":null},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Asma Khan","raw_affiliation_strings":["University of California, Irvine, Irvine, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California, Irvine, Irvine, CA, USA","institution_ids":["https://openalex.org/I204250578"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zainab Khan","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zainab Khan","raw_affiliation_strings":["Stanford University, Stanford, CA, USA"],"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Lun Bin Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210121988","display_name":"Film Independent","ror":"https://ror.org/036cy3843","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210121988"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lun Bin Huang","raw_affiliation_strings":["Independent Researcher, San Diego, CA, USA"],"affiliations":[{"raw_affiliation_string":"Independent Researcher, San Diego, CA, USA","institution_ids":["https://openalex.org/I4210121988"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Kun Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kun Wang","raw_affiliation_strings":["University of California, Los Angeles, Los Angeles, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California, Los Angeles, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"last","author":{"id":null,"display_name":"Lei He","orcid":null},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lei He","raw_affiliation_strings":["University of California, Los Angeles, Los Angeles, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California, Los Angeles, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I161318765"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I161318765"],"apc_list":null,"apc_paid":null,"fwci":4.149,"has_fulltext":false,"cited_by_count":70,"citation_normalized_percentile":{"value":0.94595235,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"227","last_page":"227"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.9988999962806702,"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":0.9988999962806702,"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/T10028","display_name":"Topic Modeling","score":0.9937999844551086,"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"}},{"id":"https://openalex.org/T12326","display_name":"Network Packet Processing and Optimization","score":0.9912999868392944,"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/overlay","display_name":"Overlay","score":0.680400013923645},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.6480000019073486},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.5722000002861023},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5354999899864197},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.47870001196861267},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4390999972820282},{"id":"https://openalex.org/keywords/edge-device","display_name":"Edge device","score":0.3849000036716461},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.37470000982284546}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8479999899864197},{"id":"https://openalex.org/C136085584","wikidata":"https://www.wikidata.org/wiki/Q910289","display_name":"Overlay","level":2,"score":0.680400013923645},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.6480000019073486},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.5722000002861023},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5354999899864197},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.47870001196861267},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4390999972820282},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4271000027656555},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.3849000036716461},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.38420000672340393},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.375900000333786},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.37470000982284546},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.34850001335144043},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.31540000438690186},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.31360000371932983},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.3125999867916107},{"id":"https://openalex.org/C19024347","wikidata":"https://www.wikidata.org/wiki/Q211496","display_name":"High-level programming language","level":3,"score":0.3095000088214874},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.28209999203681946},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.27649998664855957},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.2727999985218048},{"id":"https://openalex.org/C195818886","wikidata":"https://www.wikidata.org/wiki/Q5421724","display_name":"Expressive power","level":2,"score":0.2711000144481659},{"id":"https://openalex.org/C67463725","wikidata":"https://www.wikidata.org/wiki/Q17081452","display_name":"Natural language programming","level":5,"score":0.26589998602867126},{"id":"https://openalex.org/C46637626","wikidata":"https://www.wikidata.org/wiki/Q6693015","display_name":"Low latency (capital markets)","level":2,"score":0.26409998536109924},{"id":"https://openalex.org/C165005293","wikidata":"https://www.wikidata.org/wiki/Q1074500","display_name":"Chip","level":2,"score":0.26339998841285706},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.25130000710487366}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3431920.3439477","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3431920.3439477","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 2021 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2104.06535","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2104.06535","pdf_url":"https://arxiv.org/pdf/2104.06535","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2104.06535","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2104.06535","pdf_url":"https://arxiv.org/pdf/2104.06535","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In":[0,14,73],"recent":[1],"years,":[2],"transformer-based":[3,75],"models":[4,132],"have":[5,51],"shown":[6,53],"state-of-the-art":[7],"results":[8],"for":[9,57,122,129,144,187],"Natural":[10,188],"Language":[11,189],"Processing":[12,190],"(NLP).":[13],"particular,":[15],"the":[16,19,111,145,177,192],"introduction":[17],"of":[18,81,103],"BERT":[20,146,173],"language":[21,35,147],"model":[22,148],"brought":[23],"with":[24,45,86,149],"it":[25],"breakthroughs":[26],"in":[27,176],"tasks":[28],"such":[29],"as":[30,54],"question":[31],"answering":[32],"and":[33,60,155,183],"natural":[34],"inference,":[36],"advancing":[37],"applications":[38],"that":[39,97,118],"allow":[40],"humans":[41],"to":[42,110,171],"interact":[43],"naturally":[44],"embedded":[46],"devices.":[47],"FPGA-based":[48,94,185],"overlay":[49,95],"processors":[50],"been":[52],"effective":[55],"solutions":[56],"edge":[58],"image":[59],"video":[61],"processing":[62],"applications,":[63],"which":[64],"mostly":[65],"rely":[66],"on":[67],"low":[68],"precision":[69,83],"linear":[70],"matrix":[71],"operations.":[72],"contrast,":[74],"NLP":[76,104,131],"techniques":[77],"employ":[78],"a":[79,101,181],"variety":[80,102],"higher":[82,88],"nonlinear":[84,124],"operations":[85],"significantly":[87],"frequency.":[89],"We":[90,161],"present":[91],"NPE,":[92],"an":[93],"processor":[96],"can":[98,126,137],"efficiently":[99],"execute":[100],"models.":[105],"NPE":[106,136,164,179],"offers":[107],"software-like":[108],"programmability":[109],"end":[112],"user":[113],"and,":[114],"unlike":[115],"FPGA":[116,168],"designs":[117],"implement":[119],"specialized":[120],"accelerators":[121,175],"each":[123],"function,":[125],"be":[127],"upgraded":[128],"future":[130],"without":[133],"requiring":[134],"reconfiguration.":[135],"meet":[138],"real-time":[139],"conversational":[140],"AI":[141],"latency":[142],"targets":[143],"4x":[150],"lower":[151,157],"power":[152,158],"than":[153,159],"CPUs":[154],"6x":[156],"GPUs.":[160],"also":[162],"show":[163],"uses":[165],"3x":[166],"fewer":[167],"resources":[169],"relative":[170],"comparable":[172],"network-specific":[174],"literature.":[178],"provides":[180],"cost-effective":[182],"power-efficient":[184],"solution":[186],"at":[191],"edge.":[193]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":26},{"year":2024,"cited_by_count":20},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2021-03-01T00:00:00"}