{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T00:35:58Z","timestamp":1769733358728,"version":"3.49.0"},"reference-count":57,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,9,1]],"date-time":"2019-09-01T00:00:00Z","timestamp":1567296000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,9,1]],"date-time":"2019-09-01T00:00:00Z","timestamp":1567296000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,9,1]],"date-time":"2019-09-01T00:00:00Z","timestamp":1567296000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019,9]]},"DOI":"10.1109\/cluster.2019.8890989","type":"proceedings-article","created":{"date-parts":[[2019,11,13]],"date-time":"2019-11-13T13:00:53Z","timestamp":1573650053000},"page":"1-12","source":"Crossref","is-referenced-by-count":11,"title":["Quantifying the Impact of Memory Errors in Deep Learning"],"prefix":"10.1109","author":[{"given":"Zhao","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lei","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruizhu","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weijia","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daniel S.","family":"Katz","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","first-page":"55","article-title":"A hardware redundancy and recovery mechanism for reliable scientific computation on graphics processors","volume":"2007","author":"sheaffer","year":"2007","journal-title":"Graphics Hardware"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/1283900.1283902"},{"key":"ref33","article-title":"System resilience at extreme scale","author":"elnozahy","year":"2008","journal-title":"Tech Rep"},{"key":"ref32","first-page":"370","article-title":"Intermittent faults and effects on reliability of integrated circuits","year":"2008","journal-title":"Reliability and Maintainability Symp (RAMS)"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2005.110"},{"key":"ref30","first-page":"5","article-title":"Toward exascale resilience: 2014 update","volume":"1","author":"cappello","year":"2014","journal-title":"Supercomputing Frontiers and Innovations"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CCGRID.2010.84"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/1555815.1555771"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/1654059.1654102"},{"key":"ref34","doi-asserted-by":"crossref","first-page":"285","DOI":"10.1145\/2366231.2337192","article-title":"LOT-ECC: localized and tiered reliability mechanisms for commodity memory systems","volume":"40","author":"udipi","year":"2012","journal-title":"ACM SIGARCH Comp Arch News"},{"key":"ref28","article-title":"High-end computing resilience: Analysis of issues facing the HEC community and path-forward for research and development","author":"debardeleben","year":"2009","journal-title":"Whitepaper"},{"key":"ref27","doi-asserted-by":"crossref","first-page":"193","DOI":"10.1145\/2492101.1555372","article-title":"Dram errors in the wild: a large-scale field study","volume":"37","author":"schroeder","year":"2009","journal-title":"ACM Sigmetrics Performance Evaluation Review"},{"key":"ref29","article-title":"Fault tolerance for extreme-scale computing workshop","author":"katz","year":"2009","journal-title":"Technical Report ANL\/MCS-TM-312"},{"key":"ref2","article-title":"Scale out for large minibatch SGD: Residual network training on ImageNet-1K with improved accuracy and reduced time to train","author":"codreanu","year":"2017"},{"key":"ref1","first-page":"1","article-title":"Imagenet training in minutes","author":"you","year":"2018","journal-title":"Proceedings of the 47th International Conference on Parallel Processing"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TC.1984.1676390"},{"key":"ref23","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"lecun","year":"2015","journal-title":"Nature"},{"key":"ref26","first-page":"437","article-title":"Fault tolerant computing","volume":"1","author":"avizienis","year":"2012","journal-title":"The Evolution of Fault-Tolerant Computing In the Honor of William C Carter"},{"key":"ref25","author":"pradhan","year":"1996","journal-title":"Fault-Tolerant Computer System Design"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3126908.3126960"},{"key":"ref51","year":"2017","journal-title":"CAROL-FI GDB Fault Injector"},{"key":"ref57","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Adv in Neural Inf Proc Sys"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2004.1274045"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2003.1253181"},{"key":"ref54","article-title":"The effect of input data on program vulnerability","author":"sridharan","year":"2009","journal-title":"Workshop on System Effects of Logic Soft Errors (SELSE1)"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2014.6844486"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2017.7975296"},{"key":"ref10","article-title":"Analyzing and increasing the reliability of convolutional neural networks on gpus","author":"dos santos","year":"2018","journal-title":"IEEE Transactions on Reliability"},{"key":"ref11","first-page":"8","article-title":"Measurement and reporting of alpha particle and terrestrial cosmic ray-induced soft errors in semiconductor devices","volume":"1","year":"2006","journal-title":"JEDEC Solid state Technology Association"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2015.7056044"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2017.41"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2012.6237031"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/12.660173"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/81.390269"},{"key":"ref16","article-title":"Exploiting the tradeoff between program accuracy and soft-error resiliency overhead for machine learning workloads","author":"shi","year":"2017"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3126908.3126964"},{"key":"ref18","article-title":"Learning multiple layers of features from tiny images","author":"krizhevsky","year":"2009","journal-title":"Tech Rep"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref4","article-title":"Horovod: fast and easy distributed deep learning in TensorFlow","author":"sergeev","year":"2018"},{"key":"ref3","article-title":"Extremely large minibatch SGD: Training ResNet-50 on ImageNet in 15 minutes","author":"akiba","year":"2017"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3126908.3126916"},{"key":"ref5","article-title":"Bringing HPC techniques to deep learning","author":"gibiansky","year":"2017","journal-title":"Baidu Research Tech Rep"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1038\/nphys4035"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3126908.3126969"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2013.262"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1177\/1094342014522573"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS.2019.8702382"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/VTS.2018.8368656"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2008.4658655"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/LCA.2014.2365204"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2016.7446091"},{"key":"ref41","author":"rogers","year":"2015","journal-title":"GPU errors on HPC systems Characterization quantification and implications for architects and operations"},{"key":"ref44","first-page":"1","article-title":"Matic: Learning around errors for efficient low-voltage neural network accelerators","author":"kim","year":"2018","journal-title":"2018 Design Automation & Test in Europe Conference & Exhibition (DATE)"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TCSI.2018.2839613"}],"event":{"name":"2019 IEEE International Conference on Cluster Computing (CLUSTER)","location":"Albuquerque, NM, USA","start":{"date-parts":[[2019,9,23]]},"end":{"date-parts":[[2019,9,26]]}},"container-title":["2019 IEEE International Conference on Cluster Computing (CLUSTER)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8884608\/8890988\/08890989.pdf?arnumber=8890989","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,17]],"date-time":"2022-07-17T17:55:13Z","timestamp":1658080513000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8890989\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,9]]},"references-count":57,"URL":"https:\/\/doi.org\/10.1109\/cluster.2019.8890989","relation":{},"subject":[],"published":{"date-parts":[[2019,9]]}}}