{"id":"https://openalex.org/W3007372856","doi":"https://doi.org/10.23919/date48585.2020.9116299","title":"TFApprox: Towards a Fast Emulation of DNN Approximate Hardware Accelerators on GPU","display_name":"TFApprox: Towards a Fast Emulation of DNN Approximate Hardware Accelerators on GPU","publication_year":2020,"publication_date":"2020-03-01","ids":{"openalex":"https://openalex.org/W3007372856","doi":"https://doi.org/10.23919/date48585.2020.9116299","mag":"3007372856"},"language":"en","primary_location":{"id":"doi:10.23919/date48585.2020.9116299","is_oa":false,"landing_page_url":"https://doi.org/10.23919/date48585.2020.9116299","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 Design, Automation & Test in Europe Conference & Exhibition (DATE)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2002.09481","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Filip Vaverka","orcid":null},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":true,"raw_author_name":"Filip Vaverka","raw_affiliation_strings":["Faculty of Information Technology, IT4Innovations Centre of Excellence, Brno University of Technology, Brno, Czech Republic"],"affiliations":[{"raw_affiliation_string":"Faculty of Information Technology, IT4Innovations Centre of Excellence, Brno University of Technology, Brno, Czech Republic","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Vojtech Mrazek","orcid":null},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Vojtech Mrazek","raw_affiliation_strings":["Faculty of Information Technology, IT4Innovations Centre of Excellence, Brno University of Technology, Brno, Czech Republic"],"affiliations":[{"raw_affiliation_string":"Faculty of Information Technology, IT4Innovations Centre of Excellence, Brno University of Technology, Brno, Czech Republic","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zdenek Vasicek","orcid":null},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Zdenek Vasicek","raw_affiliation_strings":["Faculty of Information Technology, IT4Innovations Centre of Excellence, Brno University of Technology, Brno, Czech Republic"],"affiliations":[{"raw_affiliation_string":"Faculty of Information Technology, IT4Innovations Centre of Excellence, Brno University of Technology, Brno, Czech Republic","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"last","author":{"id":null,"display_name":"Lukas Sekanina","orcid":null},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Lukas Sekanina","raw_affiliation_strings":["Faculty of Information Technology, IT4Innovations Centre of Excellence, Brno University of Technology, Brno, Czech Republic"],"affiliations":[{"raw_affiliation_string":"Faculty of Information Technology, IT4Innovations Centre of Excellence, Brno University of Technology, Brno, Czech Republic","institution_ids":["https://openalex.org/I60587646"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I60587646"],"apc_list":null,"apc_paid":null,"fwci":4.9185,"has_fulltext":false,"cited_by_count":36,"citation_normalized_percentile":{"value":0.95881852,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"294","last_page":"297"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9995999932289124,"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":0.9995999932289124,"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/T10363","display_name":"Low-power high-performance VLSI design","score":0.9995999932289124,"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":0.9983999729156494,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/emulation","display_name":"Emulation","score":0.7714999914169312},{"id":"https://openalex.org/keywords/hardware-acceleration","display_name":"Hardware acceleration","score":0.5573999881744385},{"id":"https://openalex.org/keywords/central-processing-unit","display_name":"Central processing unit","score":0.5390999913215637},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5382000207901001},{"id":"https://openalex.org/keywords/floating-point","display_name":"Floating point","score":0.5080000162124634},{"id":"https://openalex.org/keywords/double-precision-floating-point-format","display_name":"Double-precision floating-point format","score":0.46230000257492065},{"id":"https://openalex.org/keywords/coprocessor","display_name":"Coprocessor","score":0.461899995803833},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.4268999993801117},{"id":"https://openalex.org/keywords/hardware-emulation","display_name":"Hardware emulation","score":0.3978999853134155}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8251000046730042},{"id":"https://openalex.org/C149810388","wikidata":"https://www.wikidata.org/wiki/Q5374873","display_name":"Emulation","level":2,"score":0.7714999914169312},{"id":"https://openalex.org/C13164978","wikidata":"https://www.wikidata.org/wiki/Q600158","display_name":"Hardware acceleration","level":3,"score":0.5573999881744385},{"id":"https://openalex.org/C49154492","wikidata":"https://www.wikidata.org/wiki/Q5300","display_name":"Central processing unit","level":2,"score":0.5390999913215637},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5382000207901001},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.5134999752044678},{"id":"https://openalex.org/C84211073","wikidata":"https://www.wikidata.org/wiki/Q117879","display_name":"Floating point","level":2,"score":0.5080000162124634},{"id":"https://openalex.org/C35912277","wikidata":"https://www.wikidata.org/wiki/Q1243369","display_name":"Double-precision floating-point format","level":3,"score":0.46230000257492065},{"id":"https://openalex.org/C86111242","wikidata":"https://www.wikidata.org/wiki/Q859595","display_name":"Coprocessor","level":2,"score":0.461899995803833},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.4268999993801117},{"id":"https://openalex.org/C94115699","wikidata":"https://www.wikidata.org/wiki/Q5656406","display_name":"Hardware emulation","level":3,"score":0.3978999853134155},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3743000030517578},{"id":"https://openalex.org/C134146338","wikidata":"https://www.wikidata.org/wiki/Q1815901","display_name":"Electronic circuit","level":2,"score":0.367000013589859},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.35530000925064087},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.3490000069141388},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.33489999175071716},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3012999892234802},{"id":"https://openalex.org/C83581934","wikidata":"https://www.wikidata.org/wiki/Q527381","display_name":"Arbitrary-precision arithmetic","level":2,"score":0.2849000096321106},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.28360000252723694},{"id":"https://openalex.org/C110305270","wikidata":"https://www.wikidata.org/wiki/Q733507","display_name":"Floating-point unit","level":3,"score":0.28220000863075256},{"id":"https://openalex.org/C84462506","wikidata":"https://www.wikidata.org/wiki/Q173142","display_name":"Digital signal processing","level":2,"score":0.2680000066757202},{"id":"https://openalex.org/C163973906","wikidata":"https://www.wikidata.org/wiki/Q649900","display_name":"Fixed-point arithmetic","level":3,"score":0.2662000060081482},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.2612000107765198},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.2551000118255615},{"id":"https://openalex.org/C187123476","wikidata":"https://www.wikidata.org/wiki/Q1197550","display_name":"Computer performance","level":2,"score":0.2547000050544739},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.251800000667572}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.23919/date48585.2020.9116299","is_oa":false,"landing_page_url":"https://doi.org/10.23919/date48585.2020.9116299","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 Design, Automation & Test in Europe Conference & Exhibition (DATE)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2002.09481","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2002.09481","pdf_url":"https://arxiv.org/pdf/2002.09481","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:2002.09481","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2002.09481","pdf_url":"https://arxiv.org/pdf/2002.09481","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1998917233","https://openalex.org/W2048266589","https://openalex.org/W2265166184","https://openalex.org/W2606722458","https://openalex.org/W2612076670","https://openalex.org/W2793950911","https://openalex.org/W2871705258","https://openalex.org/W6687483927","https://openalex.org/W6693397755","https://openalex.org/W6714058667","https://openalex.org/W6746698991","https://openalex.org/W6765768030"],"related_works":[],"abstract_inverted_index":{"Energy":[0],"efficiency":[1],"of":[2,5,38,58,151,190],"hardware":[3,33,90],"accelerators":[4],"deep":[6],"neural":[7],"networks":[8],"(DNN)":[9],"can":[10],"be":[11,106],"improved":[12],"by":[13,25],"introducing":[14],"approximate":[15,93,122,137],"arithmetic":[16,77,94],"circuits.":[17],"In":[18,109],"order":[19,110],"to":[20,105,111,185,200],"quantify":[21],"the":[22,31,39,157,160,187,191,215],"error":[23],"introduced":[24],"using":[26],"these":[27,102],"circuits":[28,123,138],"and":[29,71,79,99,101,144,169,218],"avoid":[30],"expensive":[32],"prototyping,":[34],"a":[35,62,126,147,178],"software":[36,63],"emulator":[37],"DNN":[40,64,81,128,193],"accelerator":[41,129,194],"is":[42,52,85,88,131,163,174,219],"usually":[43],"executed":[44],"on":[45,67,96,133,205],"CPU":[46,68,203],"or":[47,55,69],"GPU.":[48,134],"However,":[49],"this":[50,113],"emulation":[51,119],"typically":[53],"two":[54],"three":[56],"orders":[57],"magnitude":[59],"slower":[60],"than":[61],"implementation":[65],"running":[66],"GPU":[70,172],"operating":[72],"with":[73,198],"standard":[74],"floating":[75],"point":[76],"instructions":[78],"common":[80,97],"libraries.":[82],"The":[83,211],"reason":[84],"that":[86,159],"there":[87],"no":[89],"support":[91],"for":[92,121,165],"operations":[95,103],"CPUs":[98],"GPUs":[100],"have":[104],"expensively":[107],"emulated.":[108],"address":[112],"issue,":[114],"we":[115],"propose":[116],"an":[117,201],"efficient":[118],"method":[120],"utilized":[124],"in":[125,170],"given":[127],"which":[130],"emulated":[132,192],"All":[135],"relevant":[136],"are":[139],"implemented":[140,176],"as":[141,177,209],"look-up":[142],"tables":[143],"accessed":[145],"through":[146],"texture":[148,161],"memory":[149,162],"mechanism":[150],"CUDA":[152],"capable":[153],"GPUs.":[154],"We":[155],"exploit":[156],"fact":[158],"optimized":[164,202],"irregular":[166],"read-only":[167],"access":[168],"some":[171],"architectures":[173],"even":[175],"dedicated":[179],"cache.":[180],"This":[181],"technique":[182],"allowed":[183],"us":[184],"reduce":[186],"inference":[188],"time":[189],"approximately":[195],"200":[196],"times":[197],"respect":[199],"version":[204],"complex":[206],"DNNs":[207],"such":[208],"ResNet.":[210],"proposed":[212],"approach":[213],"extends":[214],"TensorFlow":[216],"library":[217],"available":[220],"online":[221],"at":[222],"github.com/ehw-fit/tf-approximate.":[223]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2020-03-06T00:00:00"}