{"id":"https://openalex.org/W3117765988","doi":"https://doi.org/10.1109/tpds.2020.3045828","title":"Accelerating Binarized Neural Networks via Bit-Tensor-Cores in Turing GPUs","display_name":"Accelerating Binarized Neural Networks via Bit-Tensor-Cores in Turing GPUs","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3117765988","doi":"https://doi.org/10.1109/tpds.2020.3045828","mag":"3117765988"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2020.3045828","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2020.3045828","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/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":true,"raw_author_name":"Ang Li","raw_affiliation_strings":["High-Performance Computing Group, Pacific Northwest National Laboratory (PNNL), Richland, WA, USA"],"affiliations":[{"raw_affiliation_string":"High-Performance Computing Group, Pacific Northwest National Laboratory (PNNL), Richland, WA, USA","institution_ids":["https://openalex.org/I142606810"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082646616","display_name":"Simon Su","orcid":"https://orcid.org/0000-0002-2460-3899"},"institutions":[{"id":"https://openalex.org/I166416128","display_name":"DEVCOM Army Research Laboratory","ror":"https://ror.org/011hc8f90","country_code":"US","type":"government","lineage":["https://openalex.org/I1304082316","https://openalex.org/I1330347796","https://openalex.org/I166416128","https://openalex.org/I2802705668","https://openalex.org/I4210154437"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Simon M Su","raw_affiliation_strings":["U.S. Army Research Laboratory (ARL), DoD Supercomputing Resource Center, Aberdeen Proving Ground, MD, USA"],"affiliations":[{"raw_affiliation_string":"U.S. Army Research Laboratory (ARL), DoD Supercomputing Resource Center, Aberdeen Proving Ground, MD, USA","institution_ids":["https://openalex.org/I166416128"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100413657"],"corresponding_institution_ids":["https://openalex.org/I142606810"],"apc_list":null,"apc_paid":null,"fwci":2.0624,"has_fulltext":false,"cited_by_count":37,"citation_normalized_percentile":{"value":0.89378618,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"1"},"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/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.9997000098228455,"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/T12676","display_name":"Machine Learning and ELM","score":0.9986000061035156,"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":0.8692363500595093},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7255373597145081},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5585099458694458},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.5216867923736572},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.468850702047348},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.46768954396247864},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4627950191497803},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.43930286169052124},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.42691507935523987},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.358970582485199},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.3360486626625061},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.25456055998802185},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2155967652797699}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8692363500595093},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7255373597145081},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5585099458694458},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.5216867923736572},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.468850702047348},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.46768954396247864},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4627950191497803},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.43930286169052124},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.42691507935523987},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.358970582485199},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3360486626625061},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.25456055998802185},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2155967652797699},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tpds.2020.3045828","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2020.3045828","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":100,"referenced_works":["https://openalex.org/W1530262073","https://openalex.org/W1667652561","https://openalex.org/W1686810756","https://openalex.org/W1836465849","https://openalex.org/W1902934009","https://openalex.org/W1967701350","https://openalex.org/W1976641468","https://openalex.org/W2041356909","https://openalex.org/W2047213715","https://openalex.org/W2090593986","https://openalex.org/W2091599698","https://openalex.org/W2094269606","https://openalex.org/W2108598243","https://openalex.org/W2109197177","https://openalex.org/W2163605009","https://openalex.org/W2194775991","https://openalex.org/W2267635276","https://openalex.org/W2300242332","https://openalex.org/W2319920447","https://openalex.org/W2345717615","https://openalex.org/W2410071687","https://openalex.org/W2415973476","https://openalex.org/W2483772785","https://openalex.org/W2512971201","https://openalex.org/W2565125333","https://openalex.org/W2585560244","https://openalex.org/W2591922920","https://openalex.org/W2604700561","https://openalex.org/W2605251767","https://openalex.org/W2605350416","https://openalex.org/W2606722458","https://openalex.org/W2725001169","https://openalex.org/W2747853580","https://openalex.org/W2753301142","https://openalex.org/W2765235648","https://openalex.org/W2767210925","https://openalex.org/W2791673912","https://openalex.org/W2796649226","https://openalex.org/W2808541151","https://openalex.org/W2812373594","https://openalex.org/W2886991855","https://openalex.org/W2887447938","https://openalex.org/W2891890103","https://openalex.org/W2895089194","https://openalex.org/W2895305554","https://openalex.org/W2901549770","https://openalex.org/W2903901007","https://openalex.org/W2908314593","https://openalex.org/W2911591717","https://openalex.org/W2914381000","https://openalex.org/W2920798074","https://openalex.org/W2926767350","https://openalex.org/W2949744956","https://openalex.org/W2951816500","https://openalex.org/W2952797486","https://openalex.org/W2962699575","https://openalex.org/W2962938696","https://openalex.org/W2963114950","https://openalex.org/W2963281729","https://openalex.org/W2963427045","https://openalex.org/W2963983756","https://openalex.org/W2963989532","https://openalex.org/W2964008506","https://openalex.org/W2970691381","https://openalex.org/W2971542763","https://openalex.org/W2981323010","https://openalex.org/W2981819390","https://openalex.org/W2984035546","https://openalex.org/W3000556572","https://openalex.org/W3009762362","https://openalex.org/W3040090953","https://openalex.org/W3047345547","https://openalex.org/W3101543398","https://openalex.org/W3101708369","https://openalex.org/W3102169921","https://openalex.org/W3104528661","https://openalex.org/W4295262505","https://openalex.org/W4297672357","https://openalex.org/W4302296459","https://openalex.org/W6631660994","https://openalex.org/W6637151318","https://openalex.org/W6637373629","https://openalex.org/W6638667902","https://openalex.org/W6639703010","https://openalex.org/W6684191040","https://openalex.org/W6693397755","https://openalex.org/W6700264148","https://openalex.org/W6736166019","https://openalex.org/W6740103103","https://openalex.org/W6743496644","https://openalex.org/W6744700018","https://openalex.org/W6745591726","https://openalex.org/W6750448596","https://openalex.org/W6755209637","https://openalex.org/W6757713054","https://openalex.org/W6758743346","https://openalex.org/W6760272376","https://openalex.org/W6772803787","https://openalex.org/W6774835622","https://openalex.org/W6898611122"],"related_works":["https://openalex.org/W3099313426","https://openalex.org/W2017990332","https://openalex.org/W2080337923","https://openalex.org/W4287593139","https://openalex.org/W1488776355","https://openalex.org/W2093251826","https://openalex.org/W4244262766","https://openalex.org/W752783541","https://openalex.org/W1506547947","https://openalex.org/W4206811032"],"abstract_inverted_index":{"Despite":[0],"foreseeing":[1],"tremendous":[2],"speedups":[3],"over":[4],"conventional":[5],"deep":[6],"neural":[7,14],"networks,":[8],"the":[9,56,89,108,122,127],"performance":[10,97,113],"advantage":[11],"of":[12,91,161],"binarized":[13],"networks":[15],"(BNNs)":[16],"has":[17],"merely":[18],"been":[19,44],"showcased":[20],"on":[21,143,176],"general-purpose":[22],"processors":[23],"such":[24],"as":[25],"CPUs":[26],"and":[27,81,99,132,139],"GPUs.":[28],"In":[29,69],"fact,":[30],"due":[31],"to":[32,35,64,106],"being":[33],"unable":[34],"leverage":[36],"bit-level-parallelism":[37],"with":[38,150],"a":[39,100,159],"word-based":[40],"architecture,":[41],"GPUs":[42,62,147],"have":[43],"criticized":[45],"for":[46,110,130],"extremely":[47],"low":[48],"utilization":[49],"(1":[50],"percent)":[51],"when":[52],"executing":[53],"BNNs.":[54],"Consequently,":[55],"latest":[57],"tensorcores":[58,109],"in":[59],"NVIDIA":[60,145],"Turing":[61,146],"start":[63],"experimentally":[65],"support":[66,107],"bit":[67,78,136,140],"computation.":[68],"this":[70,75],"article,":[71],"we":[72],"look":[73],"into":[74],"brand":[76],"new":[77],"computation":[79],"capability":[80],"characterize":[82],"its":[83],"unique":[84],"features.":[85],"We":[86,120],"show":[87,148],"that":[88],"stride":[90],"memory":[92],"access":[93],"can":[94,155],"significantly":[95],"affect":[96],"delivery":[98],"data-format":[101],"co-design":[102],"is":[103,174],"highly":[104],"desired":[105],"achieving":[111],"superior":[112],"than":[114,169],"existing":[115],"software":[116],"solutions":[117],"without":[118],"tensorcores.":[119],"realize":[121],"tensorcore-accelerated":[123],"BNN":[124,172],"design,":[125],"particularly":[126],"major":[128],"functions":[129],"fully-connect":[131],"convolution":[133],"layers":[134],"-":[135],"matrix":[137],"multiplication":[138],"convolution.":[141],"Evaluations":[142],"two":[144],"that,":[149],"ResNet-18,":[151],"our":[152],"BTC-BNN":[153],"design":[154],"process":[156],"ImageNet":[157],"at":[158],"rate":[160],"5.6K":[162],"images":[163],"per":[164],"second,":[165],"77":[166],"percent":[167],"faster":[168],"state-of-the-art.":[170],"Our":[171],"approach":[173],"released":[175],"https://github.com/pnnl/TCBNN.":[177]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":1}],"updated_date":"2026-03-17T09:09:15.849793","created_date":"2025-10-10T00:00:00"}