{"id":"https://openalex.org/W2591922920","doi":"https://doi.org/10.1109/fpt.2016.7929192","title":"Accelerating Binarized Neural Networks: Comparison of FPGA, CPU, GPU, and ASIC","display_name":"Accelerating Binarized Neural Networks: Comparison of FPGA, CPU, GPU, and ASIC","publication_year":2016,"publication_date":"2016-12-01","ids":{"openalex":"https://openalex.org/W2591922920","doi":"https://doi.org/10.1109/fpt.2016.7929192","mag":"2591922920"},"language":"en","primary_location":{"id":"doi:10.1109/fpt.2016.7929192","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fpt.2016.7929192","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 International Conference on Field-Programmable Technology (FPT)","raw_type":"proceedings-article"},"type":"article","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/A5084078152","display_name":"Eriko Nurvitadhi","orcid":"https://orcid.org/0000-0002-2347-9590"},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Eriko Nurvitadhi","raw_affiliation_strings":["Accelerator Architecture Lab, Intel Corporation"],"affiliations":[{"raw_affiliation_string":"Accelerator Architecture Lab, Intel Corporation","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063801377","display_name":"David Sheffield","orcid":null},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Sheffield","raw_affiliation_strings":["Accelerator Architecture Lab, Intel Corporation"],"affiliations":[{"raw_affiliation_string":"Accelerator Architecture Lab, Intel Corporation","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004251886","display_name":"Jaewoong Sim","orcid":"https://orcid.org/0000-0002-0403-9928"},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jaewoong Sim","raw_affiliation_strings":["Accelerator Architecture Lab, Intel Corporation"],"affiliations":[{"raw_affiliation_string":"Accelerator Architecture Lab, Intel Corporation","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101912070","display_name":"Asit Mishra","orcid":"https://orcid.org/0000-0001-6489-6895"},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Asit Mishra","raw_affiliation_strings":["Accelerator Architecture Lab, Intel Corporation"],"affiliations":[{"raw_affiliation_string":"Accelerator Architecture Lab, Intel Corporation","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104363400","display_name":"Ganesh Venkatesh","orcid":null},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ganesh Venkatesh","raw_affiliation_strings":["Accelerator Architecture Lab, Intel Corporation"],"affiliations":[{"raw_affiliation_string":"Accelerator Architecture Lab, Intel Corporation","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110600508","display_name":"Debbie Marr","orcid":null},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Debbie Marr","raw_affiliation_strings":["Accelerator Architecture Lab, Intel Corporation"],"affiliations":[{"raw_affiliation_string":"Accelerator Architecture Lab, Intel Corporation","institution_ids":["https://openalex.org/I1343180700"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5084078152"],"corresponding_institution_ids":["https://openalex.org/I1343180700"],"apc_list":null,"apc_paid":null,"fwci":13.8536,"has_fulltext":false,"cited_by_count":338,"citation_normalized_percentile":{"value":0.99218686,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"77","last_page":"84"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998000264167786,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9958000183105469,"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/T10320","display_name":"Neural Networks and Applications","score":0.9950000047683716,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/application-specific-integrated-circuit","display_name":"Application-specific integrated circuit","score":0.8443183898925781},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8055612444877625},{"id":"https://openalex.org/keywords/xeon","display_name":"Xeon","score":0.7910473346710205},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.7287488579750061},{"id":"https://openalex.org/keywords/hardware-acceleration","display_name":"Hardware acceleration","score":0.5219354629516602},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4913395941257477},{"id":"https://openalex.org/keywords/titan","display_name":"Titan (rocket family)","score":0.48020514845848083},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.47458577156066895},{"id":"https://openalex.org/keywords/central-processing-unit","display_name":"Central processing unit","score":0.4421422481536865},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.41784366965293884},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.394344687461853},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.11455100774765015}],"concepts":[{"id":"https://openalex.org/C77390884","wikidata":"https://www.wikidata.org/wiki/Q217302","display_name":"Application-specific integrated circuit","level":2,"score":0.8443183898925781},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8055612444877625},{"id":"https://openalex.org/C145108525","wikidata":"https://www.wikidata.org/wiki/Q656154","display_name":"Xeon","level":2,"score":0.7910473346710205},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.7287488579750061},{"id":"https://openalex.org/C13164978","wikidata":"https://www.wikidata.org/wiki/Q600158","display_name":"Hardware acceleration","level":3,"score":0.5219354629516602},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4913395941257477},{"id":"https://openalex.org/C50805821","wikidata":"https://www.wikidata.org/wiki/Q1136670","display_name":"Titan (rocket family)","level":2,"score":0.48020514845848083},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.47458577156066895},{"id":"https://openalex.org/C49154492","wikidata":"https://www.wikidata.org/wiki/Q5300","display_name":"Central processing unit","level":2,"score":0.4421422481536865},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.41784366965293884},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.394344687461853},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.11455100774765015},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/fpt.2016.7929192","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fpt.2016.7929192","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 International Conference on Field-Programmable Technology (FPT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6499999761581421,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W1836465849","https://openalex.org/W1902934009","https://openalex.org/W1905882502","https://openalex.org/W1968227766","https://openalex.org/W1980134898","https://openalex.org/W1990315422","https://openalex.org/W2022020111","https://openalex.org/W2152839228","https://openalex.org/W2163605009","https://openalex.org/W2193413348","https://openalex.org/W2319920447","https://openalex.org/W2351401301","https://openalex.org/W2527036487","https://openalex.org/W2949117887","https://openalex.org/W2963114950","https://openalex.org/W4232624858","https://openalex.org/W6639703010"],"related_works":["https://openalex.org/W2408545863","https://openalex.org/W643179351","https://openalex.org/W2905265805","https://openalex.org/W1878308862","https://openalex.org/W3193144889","https://openalex.org/W3211416786","https://openalex.org/W3003697508","https://openalex.org/W2909907505","https://openalex.org/W2073976813","https://openalex.org/W3080250604"],"abstract_inverted_index":{"Deep":[0],"neural":[1,16],"networks":[2,17],"(DNNs)":[3],"are":[4,19,142,155],"widely":[5],"used":[6],"in":[7,41,54,175],"data":[8],"analytics,":[9],"since":[10,147],"they":[11,141],"deliver":[12],"state-of-the-art":[13],"accuracies.":[14],"Binarized":[15],"(BNNs)":[18],"recently":[20],"proposed":[21,78,88],"optimized":[22,103],"variant":[23],"of":[24,71,173],"DNNs.":[25],"BNNs":[26,72,148],"constraint":[27],"network":[28],"weight":[29],"and/or":[30],"neuron":[31],"value":[32],"to":[33,46,52,65,182],"either":[34],"+1":[35],"or":[36],"\u22121,":[37],"which":[38],"is":[39,165],"representable":[40],"1":[42],"bit.":[43],"This":[44,60],"leads":[45],"dramatic":[47],"algorithm":[48],"efficiency":[49,70,126,176],"improvement,":[50],"due":[51],"reduction":[53],"the":[55,63,68,87],"memory":[56],"and":[57,99,114,129,134],"computational":[58],"demands.":[59],"paper":[61],"evaluates":[62],"opportunity":[64],"further":[66],"improve":[67],"execution":[69],"through":[73],"hardware":[74,81],"acceleration.":[75],"We":[76],"first":[77],"a":[79,185],"BNN":[80],"accelerator":[82,89],"design.":[83],"Then,":[84],"we":[85],"implemented":[86],"on":[90,105,150],"Aria":[91],"10":[92],"FPGA":[93,123,169],"as":[94,96,144],"well":[95],"14-nm":[97],"ASIC,":[98],"compared":[100],"them":[101],"against":[102],"software":[104],"Xeon":[106],"server":[107,112],"CPU,":[108],"Nvidia":[109,115],"Titan":[110],"X":[111],"GPU,":[113],"TX1":[116],"mobile":[117],"GPU.":[118,130],"Our":[119],"evaluation":[120],"shows":[121],"that":[122,154],"provides":[124],"superior":[125],"over":[127,178],"CPU":[128,133],"Even":[131],"though":[132,163],"GPU":[135],"offer":[136],"high":[137],"peak":[138],"theoretical":[139],"performance,":[140],"not":[143],"efficiently":[145],"utilized":[146],"rely":[149],"binarized":[151],"bit-level":[152],"operations":[153],"better":[156],"suited":[157],"for":[158],"custom":[159],"hardware.":[160],"Finally,":[161],"even":[162],"ASIC":[164,187],"still":[166],"more":[167],"efficient,":[168],"can":[170],"provide":[171],"orders":[172],"magnitudes":[174],"improvements":[177],"software,":[179],"without":[180],"having":[181],"lock":[183],"into":[184],"fixed":[186],"solution.":[188]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":24},{"year":2024,"cited_by_count":33},{"year":2023,"cited_by_count":45},{"year":2022,"cited_by_count":38},{"year":2021,"cited_by_count":56},{"year":2020,"cited_by_count":55},{"year":2019,"cited_by_count":39},{"year":2018,"cited_by_count":31},{"year":2017,"cited_by_count":12}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}