{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T02:55:38Z","timestamp":1773111338402,"version":"3.50.1"},"reference-count":124,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2020,8,1]],"date-time":"2020-08-01T00:00:00Z","timestamp":1596240000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,8,1]],"date-time":"2020-08-01T00:00:00Z","timestamp":1596240000000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,8,1]],"date-time":"2020-08-01T00:00:00Z","timestamp":1596240000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,8,1]],"date-time":"2020-08-01T00:00:00Z","timestamp":1596240000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["1763561"],"award-info":[{"award-number":["1763561"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Proc. IEEE"],"published-print":{"date-parts":[[2020,8]]},"DOI":"10.1109\/jproc.2020.2986362","type":"journal-article","created":{"date-parts":[[2020,5,15]],"date-time":"2020-05-15T02:51:52Z","timestamp":1589511112000},"page":"1219-1234","source":"Crossref","is-referenced-by-count":20,"title":["Addressing Unreliability in Emerging Devices and Non-von Neumann Architectures Using Coded Computing"],"prefix":"10.1109","volume":"108","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6500-2627","authenticated-orcid":false,"given":"Sanghamitra","family":"Dutta","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7862-7191","authenticated-orcid":false,"given":"Haewon","family":"Jeong","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9908-5531","authenticated-orcid":false,"given":"Yaoqing","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Viveck","family":"Cadambe","sequence":"additional","affiliation":[]},{"given":"Tze Meng","family":"Low","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7651-7776","authenticated-orcid":false,"given":"Pulkit","family":"Grover","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","article-title":"CodeNet: Training large scale neural networks in presence of soft-errors","author":"dutta","year":"2019","journal-title":"arXiv 1903 01042"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2017.2692244"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/GLOCOMW.2016.7848828"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2017.2736066"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/12.4614"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/12.59860"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT.2018.8437563"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/BigData.2018.8622429"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ALLERTON.2017.8262882"},{"key":"ref34","first-page":"2092","article-title":"Short-dot: Computing large linear transforms distributedly using coded short dot products","author":"dutta","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref28","article-title":"The landscape of parallel computing research: A view from Berkeley","author":"asanovic","year":"2006"},{"key":"ref27","article-title":"Defining software requirements for scientific computing","author":"colella","year":"2004"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TC.1984.1676475"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/1048935.1050204"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2018.2869794"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTR.2006.311846"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/2627369.2627664"},{"key":"ref23","first-page":"1","article-title":"GDOT: A graphene-based nanofunction for dot-product computation","author":"wang","year":"2016","journal-title":"Proc IEEE Symp VLSI Technol"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/ALLERTON.2018.8636047"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/2897937.2898010"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1145\/1464291.1464352"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/4.104196"},{"key":"ref50","first-page":"4302","article-title":"Gradient coding from cyclic MDS codes and expander graphs","author":"raviv","year":"2018","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref51","article-title":"Improving distributed gradient descent using Reed–Solomon codes","author":"halbawi","year":"2017","journal-title":"arXiv 1706 05436"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2019.2904055"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2018.2869791"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/3199524.3199568"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/3152042.3152047"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2019.2929328"},{"key":"ref54","first-page":"4403","article-title":"Polynomial codes: An optimal design for high-dimensional coded matrix multiplication","author":"yu","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT.2017.8006963"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ALLERTON.2017.8262883"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT.2018.8437852"},{"key":"ref4","first-page":"15","article-title":"Resilient distributed datasets: A fault-tolerant abstraction for in-memory cluster computing","author":"zaharia","year":"2012","journal-title":"Proc USENIX Symp Netw Syst Design Implem (NSDI)"},{"key":"ref3","author":"r\u00e3nnar","year":"2019","journal-title":"Parallel Computer Systems Lecture 2"},{"key":"ref6","article-title":"Dissipation of information in channels with input constraints","author":"polyanskiy","year":"2014","journal-title":"arXiv 1405 3629"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/18.796377"},{"key":"ref8","article-title":"Exascale computing study: Technology challenges in achieving exascale systems","author":"kogge","year":"2008"},{"key":"ref49","first-page":"3368","article-title":"Gradient coding: Avoiding stragglers in distributed learning","author":"tandon","year":"2017","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref7","first-page":"1","article-title":"Exascale computing technology challenges","author":"shalf","year":"2010","journal-title":"Proc Int Conf High Perform Comput Comput Sci"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/2063384.2063443"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511803253"},{"key":"ref45","article-title":"High-performance hardware for machine learning","author":"dally","year":"0"},{"key":"ref48","article-title":"Gradient coding","author":"tandon","year":"2016","journal-title":"arXiv 1612 03301"},{"key":"ref47","article-title":"A unified coded deep neural network training strategy based on generalized PolyDot codes for matrix multiplication","author":"dutta","year":"2018","journal-title":"arXiv 1811 10751"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/BF02459570"},{"key":"ref41","first-page":"329","article-title":"Probabilistic logics and the synthesis of reliable organisms from unreliable components","author":"von neumann","year":"1956","journal-title":"Automata Studies"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/SASP.2008.4570793"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CloudCom.2011.114"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2010.2054295"},{"key":"ref73","doi-asserted-by":"crossref","first-page":"225","DOI":"10.1145\/2370036.2145845","article-title":"Algorithm-based fault tolerance for dense matrix factorizations","volume":"47","author":"du","year":"2012","journal-title":"ACM SIGPLAN Notices"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1145\/1995896.1995923"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2013.111913.130178"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2013.031213.120153"},{"key":"ref76","article-title":"Coded iterative computing using substitute decoding","author":"yang","year":"2018","journal-title":"arXiv 1805 06046"},{"key":"ref77","article-title":"The PageRank citation ranking: Bringing order to the web","author":"page","year":"1999"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1145\/2686892"},{"key":"ref75","article-title":"Coded QR decomposition","author":"nguyen","year":"2020","journal-title":"Proc IEEE Int Symp Inf Theory (ISIT)"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1145\/511446.511513"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1145\/1739041.1739098"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ALLERTON.2016.7852337"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/BigData.2018.8622429"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT.2018.8437473"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682347"},{"key":"ref64","first-page":"5139","article-title":"Coded sparse matrix multiplication","author":"wang","year":"2018","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref65","article-title":"Fundamental limits of coded linear transform","author":"wang","year":"2018","journal-title":"arXiv 1804 09791"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2018.2877391"},{"key":"ref67","article-title":"3D Coded SUMMA: Communication-efficient and robust parallel matrix multiplication","author":"jeong","year":"2020","journal-title":"Proc 26th Int Eur Conf Parallel Distrib Comput"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-23397-5_10"},{"key":"ref2","article-title":"Highly scalable deep learning training system with mixed-precision: Training ImageNet in four minutes","author":"jia","year":"2018","journal-title":"arXiv 1807 11205"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/18.556667"},{"key":"ref1","author":"duranton","year":"2017","journal-title":"The HiPEAC Vision 2017"},{"key":"ref109","first-page":"199","article-title":"A 2 GHz 13.6 mW 12x9b multiplier for energy efficient FFT accelerators","author":"hsu","year":"2005","journal-title":"Proc 31st Eur Solid-State Circuits Conf (ESSCIRC)"},{"key":"ref95","article-title":"CodedSketch: A coding scheme for distributed computation of approximated matrix multiplication","author":"jahani-nezhad","year":"2018","journal-title":"arXiv 1812 10460"},{"key":"ref108","article-title":"3D-stacked memory-side acceleration: Accelerator and system design","author":"guo","year":"2014","journal-title":"Proc Workshop Near-Data Process (WoNDP) MICRO"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/BigData.2018.8622139"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1145\/2159542.2159547"},{"key":"ref93","first-page":"5606","article-title":"Communication-computation efficient gradient coding","author":"ye","year":"2018","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/12.464396"},{"key":"ref92","article-title":"Fast parallel PageRank: A linear system approach","author":"gleich","year":"2004"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/12.293265"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1137\/1.9780898718003"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/71.207595"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT.2018.8437459"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/PROC.1986.13535"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/ALLERTON.2017.8262778"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/ALLERTON.2015.7447112"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW.2017.33"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1145\/2847263.2847265"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT.2017.8006960"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/ISTC.2016.7593105"},{"key":"ref96","article-title":"On FFT-based convolutions and correlations, with application to solving Poisson’s equation in an open rectangular pipe","author":"ryne","year":"2011","journal-title":"arXiv 1111 4971"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1145\/321250.321259"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3295500.3356171"},{"key":"ref11","year":"2019","journal-title":"Fujitsu Begins Shipping Supercomputer Fugaku"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3126908.3126937"},{"key":"ref13","first-page":"2","article-title":"How to kill a supercomputer: Dirty power, cosmic rays, and bad solder","volume":"10","author":"geist","year":"2016","journal-title":"IEEE Spectr"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/2987550.2987554"},{"key":"ref15","first-page":"1","article-title":"Disks are like snowflakes: No two are alike","author":"krevat","year":"2011","journal-title":"Proc HotOS"},{"key":"ref118","first-page":"1215","article-title":"Lagrange coded computing: Optimal design for resiliency, security, and privacy","author":"yu","year":"2019","journal-title":"Proc Int Conf Artif Intell Statist (AISTATS)"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/2391229.2391236"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1145\/355887.355893"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT.2019.8849451"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/2391229.2391254"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-12-141050-6.50023-4"},{"key":"ref18","first-page":"24","article-title":"Reining in the outliers in map-reduce clusters using Mantri","volume":"10","author":"ananthanarayanan","year":"2010","journal-title":"Proceedings of the 5th USENIX Symposium on Operating Systems Design and Implementation (OSDI)"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1145\/378239.379023"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1145\/1669112.1669118"},{"key":"ref19","first-page":"185","article-title":"Effective straggler mitigation: Attack of the clones","author":"ananthanarayanan","year":"2013","journal-title":"Proc 1st USENIX Symp Netw Syst Design Implement (NSDI '04)"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1016\/S0377-0427(00)00396-4"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT.2019.8849468"},{"key":"ref113","year":"2020"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1109\/ALLERTON.2019.8919859"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1145\/1899412.1899418"},{"key":"ref115","article-title":"Numerically stable coded matrix computations via circulant and rotation matrix embeddings","author":"ramamoorthy","year":"2019","journal-title":"arXiv 1910 06515"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1561\/0100000084"},{"key":"ref89","first-page":"709","article-title":"Coded distributed computing for inverse problems","author":"yang","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2016.2603683"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1145\/2740070.2626325"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT.2013.6620242"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1016\/S0045-7949(00)00153-X"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT.2017.8007058"},{"key":"ref87","first-page":"5440","article-title":"Straggler mitigation in distributed optimization through data encoding","author":"karakus","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref88","article-title":"Straggler-resilient and communication-efficient distributed iterative linear solver","author":"haddadpour","year":"2018","journal-title":"arXiv 1806 06140"}],"container-title":["Proceedings of the IEEE"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/5\/9143211\/9093912-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5\/9143211\/09093912.pdf?arnumber=9093912","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T13:39:54Z","timestamp":1651066794000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9093912\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,8]]},"references-count":124,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/jproc.2020.2986362","relation":{},"ISSN":["0018-9219","1558-2256"],"issn-type":[{"value":"0018-9219","type":"print"},{"value":"1558-2256","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,8]]}}}