{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T16:56:38Z","timestamp":1778604998317,"version":"3.51.4"},"reference-count":33,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,5]]},"DOI":"10.1109\/ipdps.2018.00034","type":"proceedings-article","created":{"date-parts":[[2018,8,6]],"date-time":"2018-08-06T22:42:01Z","timestamp":1533595321000},"page":"244-253","source":"Crossref","is-referenced-by-count":25,"title":["BitFlow: Exploiting Vector Parallelism for Binary Neural Networks on CPU"],"prefix":"10.1109","author":[{"given":"Yuwei","family":"Hu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jidong","family":"Zhai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dinghua","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yifan","family":"Gong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuhao","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lei","family":"Su","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiangming","family":"Jin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","author":"zhuang","year":"2017","journal-title":"Flexible Network Binarization with Layer-wise Priority"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/MWSCAS.2017.8052915"},{"key":"ref31","author":"zhou","year":"2016","journal-title":"DoReFa-Net Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3020078.3021741"},{"key":"ref10","author":"jia","year":"2015","journal-title":"Convolution in Caffe a memo"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654889"},{"key":"ref12","author":"li","year":"2017","journal-title":"A 7 663-tops 8 2-w energy-efficient fpga accelerator for binary convolutional neural networks"},{"key":"ref13","author":"lin","year":"2017","journal-title":"Towards accurate binary convolutional neural network"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW.2013.207"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/FPT.2016.7929192"},{"key":"ref16","author":"paszke","year":"2017","journal-title":"Tensors and dynamic neural networks in python with strong gpu acceleration"},{"key":"ref17","author":"pedersoli","year":"2017","journal-title":"Espresso Efficient forward propagation for bcnns"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2013.44"},{"key":"ref19","author":"raiko","year":"2014","journal-title":"Techniques for learning binary stochastic feedforward neural networks"},{"key":"ref28","first-page":"20","article-title":"Blasx: A high performance level-3 blas library for heterogeneous multi-gpu computing","author":"wang","year":"2016","journal-title":"Proceedings of the 2016 International Conference on Supercomputing"},{"key":"ref4","author":"courbariaux","year":"2014","journal-title":"Low precision arithmetic for deep learning"},{"key":"ref27","doi-asserted-by":"crossref","first-page":"14","DOI":"10.1145\/2764454","article-title":"Blis: A framework for rapidly instantiating blas functionality","volume":"41","author":"van zee","year":"2015","journal-title":"ACM Transactions on Mathematical Software (TOMS)"},{"key":"ref3","author":"courbariaux","year":"2016","journal-title":"BinaryNet Training Deep Neural Networks with Weights and Activations Constrained to +1 or ?1"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1002\/nla.1808"},{"key":"ref29","author":"xianyi","year":"2016","journal-title":"OpenBLAS An Optimized BLAS Library"},{"key":"ref5","author":"courbariaux","year":"2015","journal-title":"BinaryConnect Training deep neural networks with binary weights during propagations"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/SiPS.2014.6986082"},{"key":"ref7","author":"han","year":"2015","journal-title":"Learning both weights and connections for efficient neural networks"},{"key":"ref2","first-page":"1237","article-title":"Flexible, high performance convolutional neural networks for image classification","author":"cire?an","year":"2011","journal-title":"Proc the Twenty-Second International Joint Conference on Artificial Intelligence - Volume Volume Two"},{"key":"ref9","author":"jeong","year":"2012","journal-title":"Performance of SSE and AVX Instruction Sets"},{"key":"ref1","author":"chen","year":"2015","journal-title":"Mxnet A flexible and efficient machine learning library for heterogeneous distributed systems"},{"key":"ref20","author":"rastegari","year":"2016","journal-title":"Xnor-net Imagenet classification using binary convolutional neural networks"},{"key":"ref22","author":"simonyan","year":"2014","journal-title":"Very Deep Convolutional Networks for Large-scale Image Recognition"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2003.1227801"},{"key":"ref24","year":"2017","journal-title":"Intel Math Kernel Library (Intel MKL)"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/C-M.1978.218016"},{"key":"ref26","author":"umuroglu","year":"2016","journal-title":"FINN A framework for fast scalable binarized neural network inference"},{"key":"ref25","first-page":"1:1","article-title":"Effective simd vectorization for intel xeon phi coprocessors","volume":"2015","author":"tian","year":"2016","journal-title":"Sci Program"}],"event":{"name":"2018 IEEE International Parallel and Distributed Processing Symposium (IPDPS)","location":"Vancouver, BC","start":{"date-parts":[[2018,5,21]]},"end":{"date-parts":[[2018,5,25]]}},"container-title":["2018 IEEE International Parallel and Distributed Processing Symposium (IPDPS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8424926\/8425144\/08425178.pdf?arnumber=8425178","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,26]],"date-time":"2022-01-26T15:56:55Z","timestamp":1643212615000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8425178\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,5]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/ipdps.2018.00034","relation":{},"subject":[],"published":{"date-parts":[[2018,5]]}}}