{"id":"https://openalex.org/W3047345547","doi":"https://doi.org/10.1109/tpds.2020.3013637","title":"O3BNN-R: An Out-of-Order Architecture for High-Performance and Regularized BNN Inference","display_name":"O3BNN-R: An Out-of-Order Architecture for High-Performance and Regularized BNN Inference","publication_year":2020,"publication_date":"2020-08-03","ids":{"openalex":"https://openalex.org/W3047345547","doi":"https://doi.org/10.1109/tpds.2020.3013637","mag":"3047345547"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2020.3013637","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2020.3013637","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-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/A5078443672","display_name":"Tong Geng","orcid":"https://orcid.org/0000-0002-3644-2922"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tong Geng","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Boston University, Boston, USA"],"raw_orcid":"https://orcid.org/0000-0002-3644-2922","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Boston University, Boston, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100413657","display_name":"Ang Li","orcid":"https://orcid.org/0000-0003-3734-9137"},"institutions":[{"id":"https://openalex.org/I142606810","display_name":"Pacific Northwest National Laboratory","ror":"https://ror.org/05h992307","country_code":"US","type":"facility","lineage":["https://openalex.org/I1325736334","https://openalex.org/I1330989302","https://openalex.org/I142606810","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ang Li","raw_affiliation_strings":["PCSD, Pacific Northwest National Laboratory, Richland, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"PCSD, Pacific Northwest National Laboratory, Richland, USA","institution_ids":["https://openalex.org/I142606810"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100734913","display_name":"Tianqi Wang","orcid":"https://orcid.org/0000-0002-5921-6565"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tianqi Wang","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Boston University, Boston, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Boston University, Boston, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009432979","display_name":"Chunshu Wu","orcid":"https://orcid.org/0009-0006-2039-0853"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chunshu Wu","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Boston University, Boston, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Boston University, Boston, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100414600","display_name":"Yanfei Li","orcid":"https://orcid.org/0000-0003-0812-2339"},"institutions":[{"id":"https://openalex.org/I4210119388","display_name":"Zhejiang Science and Technology Information Institute","ror":"https://ror.org/02rzte064","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210119388"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanfei Li","raw_affiliation_strings":["College of Information Science and Electronic Engineering, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Information Science and Electronic Engineering, Hangzhou, China","institution_ids":["https://openalex.org/I4210119388"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027887058","display_name":"Runbin Shi","orcid":"https://orcid.org/0000-0003-4901-5476"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Runbin Shi","raw_affiliation_strings":["Department of Electrical and Electronic Engineering, Hong Kong University, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0003-4901-5476","affiliations":[{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, Hong Kong University, Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027254893","display_name":"Wei Wu","orcid":"https://orcid.org/0000-0002-2750-6365"},"institutions":[{"id":"https://openalex.org/I1343871089","display_name":"Los Alamos National Laboratory","ror":"https://ror.org/01e41cf67","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1343871089","https://openalex.org/I198811213","https://openalex.org/I4210120050"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wei Wu","raw_affiliation_strings":["Program Model Team, Los Alamos National Laboratory (LANL), Los Alamos, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Program Model Team, Los Alamos National Laboratory (LANL), Los Alamos, USA","institution_ids":["https://openalex.org/I1343871089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021051610","display_name":"Martin Herbordt","orcid":"https://orcid.org/0000-0002-3443-9113"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Martin Herbordt","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Boston University, Boston, USA"],"raw_orcid":"https://orcid.org/0000-0002-3443-9113","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Boston University, Boston, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.6833,"has_fulltext":false,"cited_by_count":46,"citation_normalized_percentile":{"value":0.9188977,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"32","issue":"1","first_page":"199","last_page":"213"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998999834060669,"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":0.9998999834060669,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9965999722480774,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9952999949455261,"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/computer-science","display_name":"Computer science","score":0.8065444827079773},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.7262680530548096},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.7225592732429504},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.7032973766326904},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.6145616173744202},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.59588623046875},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.521014928817749},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.45581239461898804},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.4290004074573517},{"id":"https://openalex.org/keywords/performance-improvement","display_name":"Performance improvement","score":0.4259869456291199},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.39306238293647766},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.25257575511932373},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.12166076898574829}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8065444827079773},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.7262680530548096},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.7225592732429504},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7032973766326904},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.6145616173744202},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.59588623046875},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.521014928817749},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.45581239461898804},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.4290004074573517},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.4259869456291199},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.39306238293647766},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25257575511932373},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.12166076898574829},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tpds.2020.3013637","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2020.3013637","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.8899999856948853}],"awards":[{"id":"https://openalex.org/G1976304925","display_name":null,"funder_award_id":"CCF-1618303/7960","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4556659623","display_name":null,"funder_award_id":"1R41GM128533","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G8709736269","display_name":null,"funder_award_id":"CNS-1405695","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320307102","display_name":"Intel Corporation","ror":"https://ror.org/01ek73717"},{"id":"https://openalex.org/F4320307764","display_name":"Microsoft","ror":"https://ror.org/00d0nc645"},{"id":"https://openalex.org/F4320314786","display_name":"Xilinx","ror":"https://ror.org/01rb7bk56"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320338354","display_name":"Pacific Northwest National Laboratory","ror":"https://ror.org/05h992307"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":57,"referenced_works":["https://openalex.org/W1555915743","https://openalex.org/W1686810756","https://openalex.org/W1902934009","https://openalex.org/W1983364832","https://openalex.org/W2016053056","https://openalex.org/W2124446952","https://openalex.org/W2163605009","https://openalex.org/W2170585292","https://openalex.org/W2267635276","https://openalex.org/W2300242332","https://openalex.org/W2319920447","https://openalex.org/W2469490737","https://openalex.org/W2524428287","https://openalex.org/W2553910756","https://openalex.org/W2554302513","https://openalex.org/W2559305746","https://openalex.org/W2565125333","https://openalex.org/W2565305208","https://openalex.org/W2585560244","https://openalex.org/W2591922920","https://openalex.org/W2604700561","https://openalex.org/W2625954420","https://openalex.org/W2725179571","https://openalex.org/W2729080111","https://openalex.org/W2765235648","https://openalex.org/W2786098160","https://openalex.org/W2786288715","https://openalex.org/W2787766461","https://openalex.org/W2886991855","https://openalex.org/W2890068895","https://openalex.org/W2891946740","https://openalex.org/W2949744956","https://openalex.org/W2962835968","https://openalex.org/W2963114950","https://openalex.org/W2963363373","https://openalex.org/W2963427045","https://openalex.org/W2971542763","https://openalex.org/W2984035546","https://openalex.org/W3000556572","https://openalex.org/W3035430964","https://openalex.org/W3101861725","https://openalex.org/W3102169921","https://openalex.org/W3105753905","https://openalex.org/W4249932213","https://openalex.org/W4295262505","https://openalex.org/W6637373629","https://openalex.org/W6639703010","https://openalex.org/W6684191040","https://openalex.org/W6693397755","https://openalex.org/W6700264148","https://openalex.org/W6720242923","https://openalex.org/W6727208969","https://openalex.org/W6729763630","https://openalex.org/W6736166019","https://openalex.org/W6748601877","https://openalex.org/W6772803787","https://openalex.org/W6774478992"],"related_works":["https://openalex.org/W2058965144","https://openalex.org/W2164382479","https://openalex.org/W2146343568","https://openalex.org/W98480971","https://openalex.org/W2150291671","https://openalex.org/W2013643406","https://openalex.org/W2027972911","https://openalex.org/W2157978810","https://openalex.org/W4384937382","https://openalex.org/W2756666606"],"abstract_inverted_index":{"Binarized":[0],"Neural":[1],"Networks":[2],"(BNN),":[3],"which":[4,71],"significantly":[5,51],"reduce":[6],"computational":[7],"complexity":[8],"and":[9,17,23,33,103,160,188],"memory":[10],"demand,":[11],"have":[12],"shown":[13],"potential":[14],"in":[15,76],"cost-":[16],"power-restricted":[18],"domains,":[19],"such":[20],"as":[21],"IoT":[22],"smart":[24],"edge-devices,":[25],"where":[26,78,127],"reaching":[27],"certain":[28],"accuracy":[29,183],"bars":[30],"is":[31,35,93,206],"sufficient":[32],"real-time":[34],"highly":[36],"desired.":[37],"In":[38],"this":[39],"article,":[40],"we":[41,121,128],"demonstrate":[42],"that":[43,154,168],"the":[44,79,118,130,134,179,204],"highly-condensed":[45],"BNN":[46,196],"model":[47],"can":[48,72,85,172],"be":[49,86,111],"shrunk":[50],"by":[52,211],"dynamically":[53],"pruning":[54,105,119],"irregular":[55],"redundant":[56],"edges.":[57],"Based":[58],"on":[59,63,148,174,189,198,209],"two":[60],"new":[61],"observations":[62],"BNN-specific":[64],"properties,":[65],"an":[66,123,149],"out-of-order":[67],"(OoO)":[68],"architecture,":[69],"O3BNN-R,":[70],"curtail":[73],"edge":[74,142],"evaluation":[75],"cases":[77],"binary":[80],"output":[81],"of":[82,178],"a":[83,161],"neuron":[84],"determined":[87],"early":[88],"at":[89,202],"runtime":[90,104],"during":[91,133],"inference,":[92],"proposed.":[94],"Similar":[95],"to":[96,110,113],"instruction":[97],"level":[98],"parallelism":[99],"(ILP),":[100],"fine-grained,":[101],"irregular,":[102],"opportunities":[106],"are":[107],"traditionally":[108],"presumed":[109],"difficult":[112],"exploit.":[114],"To":[115],"further":[116,207],"enhance":[117],"opportunities,":[120],"conduct":[122],"algorithm/architecture":[124],"co-design":[125],"approach":[126],"augment":[129],"loss":[131],"function":[132],"training":[135],"stage":[136],"with":[137],"specialized":[138],"regularization":[139,171,201],"terms":[140],"favoring":[141],"pruning.":[143],"We":[144],"evaluate":[145],"our":[146],"design":[147],"embedded":[150],"FPGA":[151],"using":[152],"networks":[153],"include":[155],"VGG-16,":[156],"AlexNet":[157],"for":[158,164],"ImageNet,":[159],"VGG-like":[162],"network":[163],"Cifar-10.":[165],"Results":[166],"show":[167],"O3BNN-R":[169],"without":[170,181],"prune,":[173],"average,":[175,210],"30":[176],"percent":[177],"operations,":[180],"any":[182],"loss,":[184],"bringing":[185],"2.2\u00d7":[186],"inference-speedup,":[187],"average":[190],"34\u00d7":[191],"energy-efficiency":[192],"improvement":[193],"over":[194],"state-of-the-art":[195],"implementations":[197],"FPGA/GPU/CPU.":[199],"With":[200],"training,":[203],"performance":[205],"improved,":[208],"15":[212],"percent.":[213]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":12},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}