{"id":"https://openalex.org/W3033506121","doi":"https://doi.org/10.1145/3393668","title":"FPGA Logic Block Architectures for Efficient Deep Learning Inference","display_name":"FPGA Logic Block Architectures for Efficient Deep Learning Inference","publication_year":2020,"publication_date":"2020-06-03","ids":{"openalex":"https://openalex.org/W3033506121","doi":"https://doi.org/10.1145/3393668","mag":"3033506121"},"language":"en","primary_location":{"id":"doi:10.1145/3393668","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3393668","pdf_url":null,"source":{"id":"https://openalex.org/S112809824","display_name":"ACM Transactions on Reconfigurable Technology and Systems","issn_l":"1936-7406","issn":["1936-7406","1936-7414"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Reconfigurable Technology and Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://utoronto.scholaris.ca/bitstreams/e6f45d4d-d709-4ab9-be33-acc2e20c46d8/download","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010597791","display_name":"Mohamed Eldafrawy","orcid":"https://orcid.org/0000-0002-4157-8584"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Mohamed Eldafrawy","raw_affiliation_strings":["University of Toronto, Toronto, Ontario, Canada"],"raw_orcid":"https://orcid.org/0000-0002-4157-8584","affiliations":[{"raw_affiliation_string":"University of Toronto, Toronto, Ontario, Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090801235","display_name":"Andrew Boutros","orcid":"https://orcid.org/0000-0002-8044-1644"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Andrew Boutros","raw_affiliation_strings":["University of Toronto, Toronto, Ontario, Canada"],"raw_orcid":"https://orcid.org/0000-0002-8044-1644","affiliations":[{"raw_affiliation_string":"University of Toronto, Toronto, Ontario, Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035517387","display_name":"Sadegh Yazdanshenas","orcid":"https://orcid.org/0000-0002-1044-4460"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Sadegh Yazdanshenas","raw_affiliation_strings":["University of Toronto, Toronto, Ontario, Canada"],"raw_orcid":"https://orcid.org/0000-0002-1044-4460","affiliations":[{"raw_affiliation_string":"University of Toronto, Toronto, Ontario, Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030184404","display_name":"Vaughn Betz","orcid":"https://orcid.org/0000-0003-0528-6493"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Vaughn Betz","raw_affiliation_strings":["University of Toronto, Toronto, Ontario, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Toronto, Toronto, Ontario, Canada","institution_ids":["https://openalex.org/I185261750"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5010597791"],"corresponding_institution_ids":["https://openalex.org/I185261750"],"apc_list":null,"apc_paid":null,"fwci":2.4968,"has_fulltext":true,"cited_by_count":38,"citation_normalized_percentile":{"value":0.89641876,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"13","issue":"3","first_page":"1","last_page":"34"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10363","display_name":"Low-power high-performance VLSI design","score":0.9998999834060669,"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/T10363","display_name":"Low-power high-performance VLSI design","score":0.9998999834060669,"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/T11032","display_name":"VLSI and Analog Circuit Testing","score":0.9994999766349792,"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/T11522","display_name":"VLSI and FPGA Design Techniques","score":0.9987000226974487,"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":0.8032962083816528},{"id":"https://openalex.org/keywords/adder","display_name":"Adder","score":0.7369803190231323},{"id":"https://openalex.org/keywords/lookup-table","display_name":"Lookup table","score":0.6703901886940002},{"id":"https://openalex.org/keywords/logic-block","display_name":"Logic block","score":0.5762711763381958},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.5567076802253723},{"id":"https://openalex.org/keywords/single-precision-floating-point-format","display_name":"Single-precision floating-point format","score":0.5384039878845215},{"id":"https://openalex.org/keywords/critical-path-method","display_name":"Critical path method","score":0.5009968280792236},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4959968030452728},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.4444383382797241},{"id":"https://openalex.org/keywords/multiplier","display_name":"Multiplier (economics)","score":0.4443580210208893},{"id":"https://openalex.org/keywords/floating-point","display_name":"Floating point","score":0.44005703926086426},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.42415574193000793},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.4171369969844818},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.384155809879303},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3662463426589966},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.134590744972229}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8032962083816528},{"id":"https://openalex.org/C164620267","wikidata":"https://www.wikidata.org/wiki/Q376953","display_name":"Adder","level":3,"score":0.7369803190231323},{"id":"https://openalex.org/C134835016","wikidata":"https://www.wikidata.org/wiki/Q690265","display_name":"Lookup table","level":2,"score":0.6703901886940002},{"id":"https://openalex.org/C2778325283","wikidata":"https://www.wikidata.org/wiki/Q1125244","display_name":"Logic block","level":3,"score":0.5762711763381958},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.5567076802253723},{"id":"https://openalex.org/C133095886","wikidata":"https://www.wikidata.org/wiki/Q1307173","display_name":"Single-precision floating-point format","level":3,"score":0.5384039878845215},{"id":"https://openalex.org/C115874739","wikidata":"https://www.wikidata.org/wiki/Q825377","display_name":"Critical path method","level":2,"score":0.5009968280792236},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4959968030452728},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.4444383382797241},{"id":"https://openalex.org/C124584101","wikidata":"https://www.wikidata.org/wiki/Q1053266","display_name":"Multiplier (economics)","level":2,"score":0.4443580210208893},{"id":"https://openalex.org/C84211073","wikidata":"https://www.wikidata.org/wiki/Q117879","display_name":"Floating point","level":2,"score":0.44005703926086426},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.42415574193000793},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.4171369969844818},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.384155809879303},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3662463426589966},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.134590744972229},{"id":"https://openalex.org/C139719470","wikidata":"https://www.wikidata.org/wiki/Q39680","display_name":"Macroeconomics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3393668","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3393668","pdf_url":null,"source":{"id":"https://openalex.org/S112809824","display_name":"ACM Transactions on Reconfigurable Technology and Systems","issn_l":"1936-7406","issn":["1936-7406","1936-7414"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Reconfigurable Technology and Systems","raw_type":"journal-article"},{"id":"pmh:oai:utoronto.scholaris.ca:1807/101316","is_oa":true,"landing_page_url":"http://hdl.handle.net/1807/101316","pdf_url":"https://utoronto.scholaris.ca/bitstreams/e6f45d4d-d709-4ab9-be33-acc2e20c46d8/download","source":{"id":"https://openalex.org/S7407055458","display_name":"TSpace","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Thesis"}],"best_oa_location":{"id":"pmh:oai:utoronto.scholaris.ca:1807/101316","is_oa":true,"landing_page_url":"http://hdl.handle.net/1807/101316","pdf_url":"https://utoronto.scholaris.ca/bitstreams/e6f45d4d-d709-4ab9-be33-acc2e20c46d8/download","source":{"id":"https://openalex.org/S7407055458","display_name":"TSpace","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Thesis"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","score":0.46000000834465027,"display_name":"Affordable and clean energy"}],"awards":[{"id":"https://openalex.org/G4587427570","display_name":null,"funder_award_id":"EP/S030069/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W3033506121.pdf"},"referenced_works_count":92,"referenced_works":["https://openalex.org/W1498436455","https://openalex.org/W1503398984","https://openalex.org/W1506806321","https://openalex.org/W1515851193","https://openalex.org/W1554663460","https://openalex.org/W1686810756","https://openalex.org/W1802825888","https://openalex.org/W1821462560","https://openalex.org/W2005602803","https://openalex.org/W2007109372","https://openalex.org/W2027130196","https://openalex.org/W2038318386","https://openalex.org/W2048773562","https://openalex.org/W2053449529","https://openalex.org/W2061488635","https://openalex.org/W2064675550","https://openalex.org/W2072249022","https://openalex.org/W2095258817","https://openalex.org/W2097117768","https://openalex.org/W2103496339","https://openalex.org/W2107701025","https://openalex.org/W2113645429","https://openalex.org/W2116094656","https://openalex.org/W2117539524","https://openalex.org/W2119821739","https://openalex.org/W2120480077","https://openalex.org/W2121332089","https://openalex.org/W2126255765","https://openalex.org/W2135689168","https://openalex.org/W2137983211","https://openalex.org/W2140405352","https://openalex.org/W2148676074","https://openalex.org/W2171768221","https://openalex.org/W2183341477","https://openalex.org/W2194775991","https://openalex.org/W2198190323","https://openalex.org/W2264331490","https://openalex.org/W2276486856","https://openalex.org/W2279098554","https://openalex.org/W2285660444","https://openalex.org/W2291160084","https://openalex.org/W2301358467","https://openalex.org/W2405920868","https://openalex.org/W2469490737","https://openalex.org/W2520083297","https://openalex.org/W2549139847","https://openalex.org/W2560017826","https://openalex.org/W2583383421","https://openalex.org/W2584311934","https://openalex.org/W2591922920","https://openalex.org/W2604319603","https://openalex.org/W2612445135","https://openalex.org/W2739601332","https://openalex.org/W2751477244","https://openalex.org/W2766839578","https://openalex.org/W2786070938","https://openalex.org/W2787752464","https://openalex.org/W2796625795","https://openalex.org/W2804047946","https://openalex.org/W2890616119","https://openalex.org/W2901839763","https://openalex.org/W2903688003","https://openalex.org/W2903735800","https://openalex.org/W2911751195","https://openalex.org/W2915933024","https://openalex.org/W2919115771","https://openalex.org/W2948244774","https://openalex.org/W2949275038","https://openalex.org/W2950533501","https://openalex.org/W2951537853","https://openalex.org/W2955425717","https://openalex.org/W2962735857","https://openalex.org/W2962747323","https://openalex.org/W2962761403","https://openalex.org/W2962782553","https://openalex.org/W2963125010","https://openalex.org/W2963420686","https://openalex.org/W2963446712","https://openalex.org/W2963711383","https://openalex.org/W2964081807","https://openalex.org/W2964199361","https://openalex.org/W2964299589","https://openalex.org/W2982316857","https://openalex.org/W2983964638","https://openalex.org/W2991040477","https://openalex.org/W3035160371","https://openalex.org/W3101086546","https://openalex.org/W3123290820","https://openalex.org/W3147600416","https://openalex.org/W4206010581","https://openalex.org/W4238913942","https://openalex.org/W4240753366"],"related_works":["https://openalex.org/W2366554144","https://openalex.org/W1564887326","https://openalex.org/W2317826828","https://openalex.org/W2003435315","https://openalex.org/W2116803521","https://openalex.org/W2024574431","https://openalex.org/W3215589575","https://openalex.org/W2773283032","https://openalex.org/W4239932082","https://openalex.org/W2083030004"],"abstract_inverted_index":{"Reducing":[0],"the":[1,43,57,84,93,97,105,135,145,164,168],"precision":[2,26,54,59],"of":[3,39,46,61,69,79,87,138,174,189],"deep":[4],"neural":[5],"network":[6],"(DNN)":[7],"inference":[8],"accelerators":[9],"can":[10],"yield":[11],"large":[12,183],"efficiency":[13,48,86],"gains":[14,184],"with":[15,51],"little":[16],"or":[17,24],"no":[18,52],"accuracy":[19,50],"degradation":[20],"compared":[21],"to":[22,104,113,163],"half":[23],"single":[25,53],"floating-point":[27],"by":[28,141,149,177],"enabling":[29],"more":[30],"multiplication":[31],"operations":[32],"per":[33],"unit":[34],"area.":[35],"A":[36],"wide":[37],"range":[38],"precisions":[40],"fall":[41],"on":[42],"pareto-optimal":[44],"curve":[45],"hardware":[47],"vs.":[49],"dominating,":[55],"making":[56],"variable":[58],"capabilities":[60],"FPGAs":[62],"very":[63],"valuable.":[64],"We":[65],"propose":[66],"three":[67],"types":[68],"logic":[70,136,165,191],"block":[71],"architectural":[72],"enhancements":[73],"and":[74,89,100,170,179],"fully":[75],"evaluate":[76],"a":[77,114,159,187],"total":[78],"six":[80],"architectures":[81],"that":[82],"improve":[83],"area":[85,116,137,169,192],"multiplications":[88],"additions":[90],"implemented":[91],"in":[92],"soft":[94],"fabric.":[95],"Increasing":[96],"LUT":[98],"fracturability":[99],"adding":[101],"two":[102],"adders":[103],"ALM":[106],"(4-bit":[107],"Adder":[108],"Double":[109],"Chain":[110],"architecture)":[111],"leads":[112],"1.5\u00d7":[115],"reduction":[117],"for":[118,194],"arithmetic":[119],"heavy":[120],"machine":[121],"learning":[122],"(ML)":[123],"kernels,":[124],"while":[125,143],"increasing":[126,144],"their":[127],"speed.":[128],"In":[129],"addition,":[130],"this":[131],"architecture":[132],"also":[133],"reduces":[134,167],"general":[139,195],"applications":[140],"6%,":[142],"critical":[146,171],"path":[147,172],"delay":[148,173],"only":[150],"1%.":[151],"However,":[152],"our":[153],"highest":[154],"impact":[155],"option,":[156],"which":[157],"adds":[158],"9-bit":[160],"shadow":[161],"multiplier":[162],"clusters,":[166],"ML":[175],"kernels":[176],"2.4\u00d7":[178],"1.2\u00d7,":[180],"respectively.":[181],"These":[182],"come":[185],"at":[186],"cost":[188],"15%":[190],"increase":[193],"applications.":[196]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}