{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T14:27:30Z","timestamp":1760711250689,"version":"3.37.3"},"reference-count":76,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000015","name":"U.S. Department of Energy","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000015","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006132","name":"Office of Science","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006132","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Office of Advanced Scientific Computing Research, Scientific Discovery"},{"name":"Advanced Computing","award":["DE-SC0022209"],"award-info":[{"award-number":["DE-SC0022209"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Parallel Distrib. Syst."],"published-print":{"date-parts":[[2023,12]]},"DOI":"10.1109\/tpds.2023.3316011","type":"journal-article","created":{"date-parts":[[2023,9,25]],"date-time":"2023-09-25T18:31:48Z","timestamp":1695666708000},"page":"3207-3223","source":"Crossref","is-referenced-by-count":2,"title":["FT-BLAS: A Fault Tolerant High Performance BLAS Implementation on x86 CPUs"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2688-8058","authenticated-orcid":false,"given":"Yujia","family":"Zhai","sequence":"first","affiliation":[{"name":"University of California, Riverside, Riverside, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-3384-6843","authenticated-orcid":false,"given":"Elisabeth","family":"Giem","sequence":"additional","affiliation":[{"name":"University of California, Riverside, Riverside, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5328-3962","authenticated-orcid":false,"given":"Kai","family":"Zhao","sequence":"additional","affiliation":[{"name":"University of Alabama at Birmingham, Birmingham, AL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0177-502X","authenticated-orcid":false,"given":"Jinyang","family":"Liu","sequence":"additional","affiliation":[{"name":"University of California, Riverside, Riverside, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5092-3987","authenticated-orcid":false,"given":"Jiajun","family":"Huang","sequence":"additional","affiliation":[{"name":"University of California, Riverside, Riverside, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3477-8043","authenticated-orcid":false,"given":"Bryan M.","family":"Wong","sequence":"additional","affiliation":[{"name":"University of California, Riverside, Riverside, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6698-7838","authenticated-orcid":false,"given":"Christian R.","family":"Shelton","sequence":"additional","affiliation":[{"name":"University of California, Riverside, Riverside, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2578-4940","authenticated-orcid":false,"given":"Zizhong","family":"Chen","sequence":"additional","affiliation":[{"name":"University of California, Riverside, Riverside, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ftcsh.1995.532603"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ISRE.1993.324825"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/VTEST.1999.766651"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER.2015.108"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2012.29"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.2172\/1222713"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/T-ED.1979.19370"},{"key":"ref8","article-title":"Soft errors in commercial semiconductor technology: Overview and scaling trends","volume":"7","author":"Baumann","year":"2002","journal-title":"IEEE Rel. Phys. Tutorial Notes, Rel. Fundamentals"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/MSPEC.2016.7420396"},{"key":"ref10","doi-asserted-by":"crossref","DOI":"10.1145\/3126908.3126960","article-title":"Experimental and analytical study of Xeon Phi reliability","volume-title":"Proc. Int. Conf. High Perform. Comput. Netw. Storage Anal.","author":"Oliveira"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3458336.3465297"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/iolts59296.2023.10224872"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1002\/jcc.20289"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.5555\/3454287.3455008"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3208040.3208050"},{"article-title":"TensorFlow: Large-scale machine learning on heterogeneous systems","year":"2015","author":"Abadi","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2014.2320502"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/HASE.2008.13"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2008.4536158"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/VLSI-TSA.2014.6839639"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2014.53"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1177\/1094342010391989"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3078597.3078617"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1177\/1094342014522573"},{"key":"ref25","doi-asserted-by":"crossref","DOI":"10.1145\/3126908.3126964","article-title":"Understanding error propagation in deep learning neural network (DNN) accelerators and applications","volume-title":"Proc. Int. Conf. High Perform. Comput. Netw. Storage Anal.","author":"Li"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/24.994913"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/24.994926"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CGO.2005.34"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CGO.2009.14"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/2903150.2903170"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TC.1984.1676475"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/DSN.2012.6263938"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/2530268.2530272"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2016.2517639"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2015.05.187"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3295500.3356195"},{"key":"ref37","doi-asserted-by":"crossref","DOI":"10.1145\/3126908.3126915","article-title":"Correcting soft errors online in fast Fourier transform","volume-title":"Proc. Int. Conf. High Perform. Comput. Netw. Storage Anal.","author":"Liang"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/BF00930642"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/71.207595"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/2517327.2442533"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/2907294.2907306"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/PADSW.2014.7097827"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2020.3043449"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3330345.3330373"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/j.parco.2014.09.001"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2015.108"},{"key":"ref47","first-page":"1","article-title":"A description of the advanced research WRF version 3, NCAR technical note","author":"Skamarock","year":"2008"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1002\/jcc.27058"},{"year":"2009","key":"ref49","article-title":"Intel Math Kernel Library"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-8191(00)00087-9"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/2764454"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/2503210.2503219"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/SC.1998.10004"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1016\/j.jocs.2013.05.002"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/DSN.2001.941390"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2008.58"},{"article-title":"Toward ABFT for BLIS GEMM","year":"2015","author":"Smith","key":"ref57"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2014.110"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/2600212.2600232"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/2907294.2907315"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2016.81"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1145\/2907294.2907321"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1145\/3447818.3460364"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/3577193.3593715"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1145\/3588195.3595947"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS53621.2022.00074"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS54959.2023.00042"},{"key":"ref68","article-title":"A high-performance implementation of atomistic spin dynamics simulations on x86 CPUs","volume-title":"Comput. Phys. Commun.","volume":"291","author":"Chen","year":"2023"},{"key":"ref69","first-page":"25","article-title":"Transient fault detection via simultaneous multithreading","volume-title":"Proc. 27th Int. Symp. Comput. Archit.","author":"Reinhardt"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1137\/1.9780898719604"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1145\/17356.17401"},{"year":"2019","key":"ref74","article-title":"Intel 64 and IA-32 architectures optimization reference manual"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1145\/1377603.1377607"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1145\/1064978.1065034"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1145\/3075564.3075598"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2014.128"}],"container-title":["IEEE Transactions on Parallel and Distributed Systems"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/71\/10272650\/10262212-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/71\/10272650\/10262212.pdf?arnumber=10262212","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,14]],"date-time":"2024-03-14T08:35:04Z","timestamp":1710405304000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10262212\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12]]},"references-count":76,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tpds.2023.3316011","relation":{},"ISSN":["1045-9219","1558-2183","2161-9883"],"issn-type":[{"type":"print","value":"1045-9219"},{"type":"electronic","value":"1558-2183"},{"type":"electronic","value":"2161-9883"}],"subject":[],"published":{"date-parts":[[2023,12]]}}}