{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T06:29:07Z","timestamp":1730269747503,"version":"3.28.0"},"reference-count":23,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,5]]},"DOI":"10.1109\/ipdpsw.2018.00138","type":"proceedings-article","created":{"date-parts":[[2018,8,6]],"date-time":"2018-08-06T22:56:37Z","timestamp":1533596197000},"page":"867-876","source":"Crossref","is-referenced-by-count":1,"title":["Streaming Tiles: Flexible Implementation of Convolution Neural Networks Inference on Manycore Architectures"],"prefix":"10.1109","author":[{"given":"Nesma M.","family":"Rezk","sequence":"first","affiliation":[]},{"given":"Madhura","family":"Purnaprajna","sequence":"additional","affiliation":[]},{"given":"Zain","family":"Ul-Abdin","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"journal-title":"Tech Rep","article-title":"White paper: Deep learning of high performance embedded applications","year":"2016","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/2968455.2968511"},{"key":"ref12","article-title":"Binarynet: Training deep neural networks with weights and activations constrained to +1 or-1","volume":"abs 1602 2830","author":"courbariaux","year":"2016","journal-title":"CoRR"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3020078.3021741"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"journal-title":"Epiphany-v A 1024 processor 64-bit risc system-on-chip","year":"2016","author":"olofsson","key":"ref15"},{"key":"ref16","article-title":"Kick-starting high-performance energy-efficient manycore architectures with epiphany","author":"olofsson","year":"2014","journal-title":"Proc of the 48th Asilomar Conf on Signals Syst and Comp"},{"key":"ref17","article-title":"A 1024-core 70 gflop\/w floating point manycore microprocessor","author":"raikhman","year":"2011","journal-title":"Poster on 15th Workshop on High Performance Embedded Computing HPEC2011"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2017.2761740"},{"key":"ref19","article-title":"Going deeper with convolutions","volume":"abs 1409 4842","author":"szegedy","year":"2014","journal-title":"CoRR"},{"key":"ref4","article-title":"Very deep convolutional networks for large-scale image recognition","volume":"abs 1409 1556","author":"simonyan","year":"2014","journal-title":"CoRR"},{"key":"ref3","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Advances in Neural Information Processing Systems 25"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2016.2616357"},{"key":"ref5","first-page":"281","author":"cong","year":"2014","journal-title":"Minimizing Computation in Convolutional Neural Networks"},{"key":"ref8","article-title":"Ternary neural networks for resource-efficient ai applications","volume":"abs 1609 222","author":"alemdar","year":"2016","journal-title":"International Joint Conference on Neural Networks"},{"key":"ref7","article-title":"Low precision arithmetic for deep learning","volume":"abs 1412 7024","author":"courbariaux","year":"2014","journal-title":"CoRR"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.2016.7474340"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ROMAN.2013.6628440"},{"key":"ref9","first-page":"3123","article-title":"Bina-ryconnect: Training deep neural networks with binary weights during propagations","author":"courbariaux","year":"2015","journal-title":"Advances in Neural IInformation Processing Systems"},{"journal-title":"Tech Rep","article-title":"White paper: Deep learning on mppa manycore processor","year":"2015","key":"ref20"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"journal-title":"Tech Rep","article-title":"White paper: Nvidia tegra x1: Nvidia's new mobile superchip","year":"2015","key":"ref21"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.2352\/ISSN.2470-1173.2017.19.AVM-023"}],"event":{"name":"2018 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW)","start":{"date-parts":[[2018,5,21]]},"location":"Vancouver, BC","end":{"date-parts":[[2018,5,25]]}},"container-title":["2018 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8424927\/8425307\/08425505.pdf?arnumber=8425505","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2018,8,20]],"date-time":"2018-08-20T22:49:57Z","timestamp":1534805397000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8425505\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,5]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/ipdpsw.2018.00138","relation":{},"subject":[],"published":{"date-parts":[[2018,5]]}}}