{"id":"https://openalex.org/W2902058806","doi":"https://doi.org/10.23919/date.2019.8715007","title":"NTX: An Energy-efficient Streaming Accelerator for Floating-point Generalized Reduction Workloads in 22 nm FD-SOI","display_name":"NTX: An Energy-efficient Streaming Accelerator for Floating-point Generalized Reduction Workloads in 22 nm FD-SOI","publication_year":2019,"publication_date":"2019-03-01","ids":{"openalex":"https://openalex.org/W2902058806","doi":"https://doi.org/10.23919/date.2019.8715007","mag":"2902058806"},"language":"en","primary_location":{"id":"doi:10.23919/date.2019.8715007","is_oa":false,"landing_page_url":"https://doi.org/10.23919/date.2019.8715007","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 Design, Automation & Test in Europe Conference & Exhibition (DATE)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/11585/702263","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5024145677","display_name":"Fabian Schuiki","orcid":"https://orcid.org/0000-0002-9923-5031"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Fabian Schuiki","raw_affiliation_strings":["IIS, ETH Z\u00fcrich, Z\u00fcrich, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIS, ETH Z\u00fcrich, Z\u00fcrich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048307575","display_name":"Michael Schaffner","orcid":"https://orcid.org/0000-0002-3244-2693"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Michael Schaffner","raw_affiliation_strings":["IIS, ETH Z\u00fcrich, Z\u00fcrich, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIS, ETH Z\u00fcrich, Z\u00fcrich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043408422","display_name":"Luca Benini","orcid":"https://orcid.org/0000-0001-8068-3806"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Luca Benini","raw_affiliation_strings":["IIS, ETH Z\u00fcrich, Z\u00fcrich, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIS, ETH Z\u00fcrich, Z\u00fcrich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9687,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":{"value":0.75481656,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"662","last_page":"667"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9994000196456909,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9994000196456909,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9993000030517578,"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":0.9980999827384949,"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/computer-science","display_name":"Computer science","score":0.7968941926956177},{"id":"https://openalex.org/keywords/coprocessor","display_name":"Coprocessor","score":0.7472050786018372},{"id":"https://openalex.org/keywords/floating-point","display_name":"Floating point","score":0.5896319150924683},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.5337516069412231},{"id":"https://openalex.org/keywords/efficient-energy-use","display_name":"Efficient energy use","score":0.49186277389526367},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.4855729937553406},{"id":"https://openalex.org/keywords/instruction-set","display_name":"Instruction set","score":0.45194438099861145},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4516158103942871},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.38984864950180054},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3531981110572815},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.342023640871048},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.17637285590171814},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.1571618616580963},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.12955933809280396},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08126378059387207}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7968941926956177},{"id":"https://openalex.org/C86111242","wikidata":"https://www.wikidata.org/wiki/Q859595","display_name":"Coprocessor","level":2,"score":0.7472050786018372},{"id":"https://openalex.org/C84211073","wikidata":"https://www.wikidata.org/wiki/Q117879","display_name":"Floating point","level":2,"score":0.5896319150924683},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.5337516069412231},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.49186277389526367},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.4855729937553406},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.45194438099861145},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4516158103942871},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.38984864950180054},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3531981110572815},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.342023640871048},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.17637285590171814},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.1571618616580963},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.12955933809280396},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08126378059387207},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.23919/date.2019.8715007","is_oa":false,"landing_page_url":"https://doi.org/10.23919/date.2019.8715007","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 Design, Automation & Test in Europe Conference & Exhibition (DATE)","raw_type":"proceedings-article"},{"id":"pmh:oai:cris.unibo.it:11585/702263","is_oa":true,"landing_page_url":"https://ieeexplore.ieee.org/document/8715007","pdf_url":"http://hdl.handle.net/11585/702263","source":{"id":"https://openalex.org/S4306402579","display_name":"Archivio istituzionale della ricerca (Alma Mater Studiorum Universit\u00e0 di Bologna)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210117483","host_organization_name":"Istituto di Ematologia di Bologna","host_organization_lineage":["https://openalex.org/I4210117483"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:cris.unibo.it:11585/702263","is_oa":true,"landing_page_url":"https://ieeexplore.ieee.org/document/8715007","pdf_url":"http://hdl.handle.net/11585/702263","source":{"id":"https://openalex.org/S4306402579","display_name":"Archivio istituzionale della ricerca (Alma Mater Studiorum Universit\u00e0 di Bologna)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210117483","host_organization_name":"Istituto di Ematologia di Bologna","host_organization_lineage":["https://openalex.org/I4210117483"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.8999999761581421}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2902058806.pdf","grobid_xml":"https://content.openalex.org/works/W2902058806.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W1966040142","https://openalex.org/W2064451896","https://openalex.org/W2091902424","https://openalex.org/W2097117768","https://openalex.org/W2107725926","https://openalex.org/W2134573462","https://openalex.org/W2163605009","https://openalex.org/W2166522594","https://openalex.org/W2183341477","https://openalex.org/W2194775991","https://openalex.org/W2518511512","https://openalex.org/W2522548197","https://openalex.org/W2604319603","https://openalex.org/W2605347906","https://openalex.org/W2626991402","https://openalex.org/W2963255460","https://openalex.org/W2963566954","https://openalex.org/W3004480871","https://openalex.org/W3105314253","https://openalex.org/W4247470470","https://openalex.org/W6684191040","https://openalex.org/W6684484575","https://openalex.org/W6748977023","https://openalex.org/W6786062839"],"related_works":["https://openalex.org/W2370279919","https://openalex.org/W2152301037","https://openalex.org/W2094210932","https://openalex.org/W1836109266","https://openalex.org/W2384717171","https://openalex.org/W2027246841","https://openalex.org/W2080109495","https://openalex.org/W2132643331","https://openalex.org/W2130912976","https://openalex.org/W2163928768"],"abstract_inverted_index":{"Specialized":[0],"coprocessors":[1],"for":[2,32,141],"Multiply-Accumulate":[3],"(MAC)":[4],"intensive":[5],"workloads":[6,172],"such":[7],"as":[8,39],"Deep":[9,34],"Learning":[10],"are":[11,60],"becoming":[12],"widespread":[13],"in":[14,67,82],"SoC":[15],"platforms,":[16],"from":[17,185],"GPUs":[18,128],"to":[19,63,91,94,116,163,188],"mobile":[20],"SoCs.":[21],"In":[22],"this":[23],"paper":[24],"we":[25,107],"revisit":[26],"NTX":[27,113,158],"(an":[28],"efficient":[29],"accelerator":[30],"developed":[31],"training":[33,142],"Neural":[35],"Networks":[36],"at":[37,97,129,181],"scale)":[38],"a":[40,51,64,78,110,121,135],"generalized":[41],"MAC":[42],"and":[43,73,100,134],"reduction":[44,171],"streaming":[45,57],"engine.":[46],"The":[47],"architecture":[48,178],"consists":[49],"of":[50,53,69,77,112,138,153,165],"set":[52],"32":[54],"bit":[55],"floating-point":[56,148],"co-processors":[58],"that":[59,109,157],"loosely":[61],"coupled":[62],"RISC-V":[65],"core":[66],"charge":[68],"orchestrating":[70],"data":[71],"movement":[72],"computation.":[74],"Post-layout":[75],"results":[76,106],"recent":[79],"silicon":[80,132],"implementation":[81],"22":[83],"nm":[84,118],"FD-SOI":[85],"technology":[86],"show":[87,108],"the":[88],"accelerator's":[89],"capability":[90],"deliver":[92],"up":[93,162],"20":[95],"Gflop/s":[96],"1.25":[98],"GHz":[99],"168":[101],"mW.":[102],"Based":[103],"on":[104],"these":[105],"version":[111],"scaled":[114],"down":[115],"14":[117],"can":[119,159],"achieve":[120,161],"3\u00d7":[122],"energy":[123],"efficiency":[124],"improvement":[125],"over":[126],"contemporary":[127],"10.4\u00d7":[130],"less":[131],"area,":[133],"compute":[136],"performance":[137,168],"1.4":[139],"Tflop/s":[140],"large":[143],"state-of-the-art":[144],"networks":[145],"with":[146],"full":[147],"precision.":[149],"An":[150],"extended":[151],"evaluation":[152],"MAC-intensive":[154],"kernels":[155],"shows":[156],"consistently":[160],"87%":[164],"its":[166],"peak":[167],"across":[169],"general":[170],"beyond":[173],"machine":[174],"learning.":[175],"Its":[176],"modular":[177],"enables":[179],"deployment":[180],"different":[182],"scales":[183],"ranging":[184],"high-performance":[186],"GPU-class":[187],"low-power":[189],"embedded":[190],"scenarios.":[191]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}