{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,23]],"date-time":"2024-10-23T01:30:04Z","timestamp":1729647004295,"version":"3.28.0"},"reference-count":45,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,5]]},"DOI":"10.1109\/ipdpsw.2018.00098","type":"proceedings-article","created":{"date-parts":[[2018,8,6]],"date-time":"2018-08-06T22:56:37Z","timestamp":1533596197000},"page":"589-598","source":"Crossref","is-referenced-by-count":16,"title":["Exploring the Vision Processing Unit as Co-Processor for Inference"],"prefix":"10.1109","author":[{"given":"Sergio","family":"Rivas-Gomez","sequence":"first","affiliation":[]},{"given":"Antonio J.","family":"Pena","sequence":"additional","affiliation":[]},{"given":"David","family":"Moloney","sequence":"additional","affiliation":[]},{"given":"Erwin","family":"Laure","sequence":"additional","affiliation":[]},{"given":"Stefano","family":"Markidis","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","first-page":"215","article-title":"An analysis of single-layer networks in unsupervised feature learning","author":"coates","year":"2011","journal-title":"Proceedings of the 14th International Conference on Artificial Intelligence and Statistics Conference (AISTATS 2011)"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553486"},{"key":"ref33","article-title":"Technical introduction to OpenEXR","author":"kainz","year":"2009","journal-title":"Industrial Light & Magic"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/2831129.2831131"},{"journal-title":"in Movid-ius com","article-title":"Myriad Development Kit (MDK): Development suite for the MA2×5x family of VPUs","year":"2016","key":"ref31"},{"journal-title":"Using MPI-2 Advanced Features of the Message-Passing Interface","year":"2014","author":"gropp","key":"ref30"},{"key":"ref37","article-title":"Benchmarking of CNNs for low-cost, low-power robotics applications","author":"pena","year":"2017","journal-title":"Proceedings of the Workshop on New Frontiers for Deep Learning in Robotics (RSS 2017)"},{"key":"ref36","article-title":"Intel launches Movidius Neural Compute Stick","author":"oh","year":"2017","journal-title":"AnandTech"},{"key":"ref35","article-title":"The data that transformed AI research, and possibly the world","author":"gershgorn","year":"2017","journal-title":"Quartz"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/219717.219748"},{"journal-title":"Training deep neural networks with low precision multiplications","year":"2014","author":"courbariaux","key":"ref10"},{"journal-title":"Nvidia tesla v100 gpu architecture","year":"2017","key":"ref40"},{"key":"ref11","first-page":"1740","article-title":"Flexpoint: An adaptive numerical format for efficient training of deep neural networks","author":"k\u00f6ster","year":"2017","journal-title":"Advances in Neural Information Processing Systems 30 (NIPS 2017)"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/MSPEC.2018.8241739"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/HOTCHIPS.2014.7478823"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2015.10"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"journal-title":"Comp Intel","article-title":"Intel democratizes deep learning application development with the launch of the Movidius Neural Compute Stick","year":"2017","key":"ref16"},{"journal-title":"Caffe Convolutional Architecture for Fast Feature Embedding","year":"2014","author":"jia","key":"ref17"},{"journal-title":"GitHub com","article-title":"Movidius Neural Compute SDK for the Neural Compute Stick platform","year":"2017","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2010.107"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/HOTCHIPS.2011.7477507"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1177\/1094342010391989"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"journal-title":"Data Mining Practical Machine Learning Tools and Techniques","year":"2016","author":"witten","key":"ref6"},{"journal-title":"Tensorflow Large-scale machine learning on heterogeneous distributed systems","year":"2016","author":"abadi","key":"ref29"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"97","DOI":"10.1109\/TKDE.2013.109","article-title":"Data Mining with Big Data","volume":"26","author":"wu","year":"2014","journal-title":"IEEE Transactions on Knowledge and Data Engineering (TKDE)"},{"journal-title":"The SAGE project Data storage for extreme scale","year":"2016","key":"ref8"},{"key":"ref7","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"loffe","year":"2015","journal-title":"Proceedings of the 32nd International Conference on Machine Learning (ICML 2015)"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1088\/0004-637X\/812\/1\/46"},{"key":"ref9","article-title":"Oak Ridge readies Summit supercomputer for 2018 debut","author":"feldman","year":"2017","journal-title":"Top500 org"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1093\/mnras\/stt1306"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/2830772.2830807"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2015.2444393"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2015.230"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/2540708.2540717"},{"key":"ref42","doi-asserted-by":"crossref","first-page":"295","DOI":"10.1145\/2668332.2668349","article-title":"DSP. Ear: Leveraging co-processor support for continuous audio sensing on smartphones","author":"georgiev","year":"2014","journal-title":"Proceedings of the 12th ACM Conference on Embedded Network Sensor Systems (SenSys 2014)"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2010.41"},{"journal-title":"Comp Intel","article-title":"Intel Nervana Neural Network Processor: Architecture update","year":"2017","key":"ref41"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCD.2016.7753257"},{"key":"ref44","article-title":"Intel Xeon Phi coprocessor-The architecture","author":"chrysos","year":"2014","journal-title":"Intel White Paper"},{"key":"ref26","doi-asserted-by":"crossref","first-page":"6","DOI":"10.1109\/MM.2015.4","article-title":"The Movidius Myriad architecture's potential for Scientific Computing","volume":"35","author":"lonica","year":"2015","journal-title":"IEEE Micro"},{"key":"ref43","first-page":"1","article-title":"Benchmarking data analysis and machine learning applications on the Intel KNL manycore processor","author":"byun","year":"2017","journal-title":"High Performance Extreme Computing Conference (HPEC) 2017 IEEE"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2011.5762730"}],"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\/08425465.pdf?arnumber=8425465","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,28]],"date-time":"2022-08-28T20:43:35Z","timestamp":1661719415000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8425465\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,5]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/ipdpsw.2018.00098","relation":{},"subject":[],"published":{"date-parts":[[2018,5]]}}}