{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T15:19:45Z","timestamp":1774365585214,"version":"3.50.1"},"reference-count":75,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"U.S. DOE Office of Science Office of Advanced Scientific Computing Research","award":["66150: CENATE - Center for Advanced Architecture E"],"award-info":[{"award-number":["66150: CENATE - Center for Advanced Architecture E"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Parallel Distrib. Syst."],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/tpds.2020.3045828","type":"journal-article","created":{"date-parts":[[2020,12,22]],"date-time":"2020-12-22T20:27:49Z","timestamp":1608668869000},"page":"1-1","source":"Crossref","is-referenced-by-count":22,"title":["Accelerating Binarized Neural Networks via Bit-Tensor-Cores in Turing GPUs"],"prefix":"10.1109","author":[{"given":"Ang","family":"Li","sequence":"first","affiliation":[]},{"given":"Simon M","family":"Su","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2019.2928289"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/FCCM.2018.00018"},{"key":"ref71","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014"},{"key":"ref70","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc 25th Int Conf Neural Inf Process Syst"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2018.8573483"},{"key":"ref39","article-title":"Embedded binarized neural networks","author":"mcdanel","year":"2017"},{"key":"ref75","article-title":"NVIDIA collective communications library","year":"0"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/2925426.2926255"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/2001858.2002031"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.cpc.2010.05.005"},{"key":"ref31","article-title":"CUDA template library for dense linear algebra at all levels and scales (CUTLASS)","year":"2018"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.3390\/electronics8060661"},{"key":"ref37","article-title":"Binary generative adversarial networks for image retrieval","author":"song","year":"2017"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/2925426.2926259"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2013.05.067"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/2504730.2504756"},{"key":"ref60","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"Proc 32nd Int Conf Mach Learn"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1145\/3126908.3126950"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1145\/2807591.2807606"},{"key":"ref28","article-title":"High performance convolutional neural networks for document processing","author":"chellapilla","year":"2006","journal-title":"Proc of the Int Conf on Frontiers in Handwriting Recognition"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/2749246.2749265"},{"key":"ref27","article-title":"NVIDIA turing GPU architecture","year":"2019"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2016.89"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.3850\/9783981537079_0394"},{"key":"ref29","article-title":"cuDNN: Efficient primitives for deep learning","author":"chetlur","year":"2014"},{"key":"ref67","article-title":"MNIST handwritten digit database","author":"lecun","year":"2010"},{"key":"ref68","article-title":"The CIFAR-10 dataset","author":"krizhevsky","year":"2014"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref2","first-page":"4114","article-title":"Binarized neural networks","author":"hubara","year":"2016","journal-title":"Proc 30th Int Conf Neural Inf Process Syst"},{"key":"ref1","article-title":"Binarized neural networks: Training deep neural networks with weights and activations constrained to+ 1 or-1","author":"courbariaux","year":"2016"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/FPT.2016.7929192"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3020078.3021741"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3020078.3021744"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ASAP.2019.00-43"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2017.09.046"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3295500.3356169"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3330345.3330386"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2018.00050"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/HiPCW.2018.8634417"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/3205289.3205294"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/3037697.3037709"},{"key":"ref57","article-title":"CUDA programming guide","year":"2018"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/2063384.2063431"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/2751205.2751232"},{"key":"ref54","article-title":"NVIDIA tesla V100 GPU architecture","year":"2017"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3330345.3331057"},{"key":"ref52","article-title":"Mixed precision block fused multiply-add: Error analysis and application to GPU tensor cores","author":"blanchard","year":"2019"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_44"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00506"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2018.00034"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00244"},{"key":"ref13","article-title":"MeliusNet: Can binary neural networks achieve MobileNet-level accuracy?","author":"bethge","year":"2020"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/669"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-94144-8_27"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2018.2840598"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/2959100.2959190"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3038912.3052569"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2020.3006238"},{"key":"ref4","first-page":"3123","article-title":"BinaryConnect: Training deep neural networks with binary weights during propagations","author":"courbariaux","year":"2015","journal-title":"Proc 28th Int Conf Neural Inf Process Syst"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_32"},{"key":"ref6","article-title":"Combinatorial attacks on binarized neural networks","author":"khalil","year":"2018"},{"key":"ref5","article-title":"Attacking binarized neural networks","author":"galloway","year":"2017"},{"key":"ref8","article-title":"BNN+: Improved binary network training","author":"darabi","year":"2018"},{"key":"ref7","first-page":"2625","article-title":"How to train a compact binary neural network with high accuracy?","author":"tang","year":"2017","journal-title":"Proc 31st AAAI Conf Artif Intell"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ARITH.2019.00031"},{"key":"ref9","article-title":"Self-binarizing networks","author":"lahoud","year":"2019"},{"key":"ref46","article-title":"Dissecting the NVidia turing T4 GPU via microbenchmarking","author":"jia","year":"2019"},{"key":"ref45","article-title":"Dissecting the NVIDIA Volta GPU architecture via microbenchmarking","author":"jia","year":"2018"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2019.00016"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW.2018.00091"},{"key":"ref42","first-page":"344","article-title":"Towards accurate binary convolutional neural network","author":"lin","year":"2017","journal-title":"Proc 31st Int Conf Neural Inf Process Syst"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2020.3013637"},{"key":"ref44","article-title":"Volta architecture White Paper","year":"2018"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080246"}],"container-title":["IEEE Transactions on Parallel and Distributed Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/71\/4359390\/09303370.pdf?arnumber=9303370","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:50:30Z","timestamp":1652194230000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9303370\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":75,"URL":"https:\/\/doi.org\/10.1109\/tpds.2020.3045828","relation":{},"ISSN":["1045-9219","1558-2183","2161-9883"],"issn-type":[{"value":"1045-9219","type":"print"},{"value":"1558-2183","type":"electronic"},{"value":"2161-9883","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]}}}