{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T10:57:17Z","timestamp":1777546637790,"version":"3.51.4"},"reference-count":47,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2017,10,1]],"date-time":"2017-10-01T00:00:00Z","timestamp":1506816000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2017,10,1]],"date-time":"2017-10-01T00:00:00Z","timestamp":1506816000000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2017,10,1]],"date-time":"2017-10-01T00:00:00Z","timestamp":1506816000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2017,10,1]],"date-time":"2017-10-01T00:00:00Z","timestamp":1506816000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation (NSF)","doi-asserted-by":"publisher","award":["ACI 1339036"],"award-info":[{"award-number":["ACI 1339036"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation (NSF)","doi-asserted-by":"publisher","award":["ACI 1310283"],"award-info":[{"award-number":["ACI 1310283"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation (NSF)","doi-asserted-by":"publisher","award":["CNS 1305375"],"award-info":[{"award-number":["CNS 1305375"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation (NSF)","doi-asserted-by":"publisher","award":["DMS 1228203"],"award-info":[{"award-number":["DMS 1228203"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Office of Advanced Scientific Computing Research"},{"DOI":"10.13039\/100006132","name":"Office of Science","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006132","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000015","name":"US Department of Energy","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000015","id-type":"DOI","asserted-by":"publisher"}]},{"name":"SciDAC Institute for Scalable Data Management"},{"name":"Analysis and Visualization (SDAV)","award":["DE-SC0007455"],"award-info":[{"award-number":["DE-SC0007455"]}]},{"DOI":"10.13039\/100012093","name":"RSVP","doi-asserted-by":"crossref","award":["4000126989"],"award-info":[{"award-number":["4000126989"]}],"id":[{"id":"10.13039\/100012093","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/100005930","name":"ASCR","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100005930","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006207","name":"FES","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006207","id-type":"DOI","asserted-by":"publisher"}]},{"name":"EPSI","award":["DE-FG02-06ER54857"],"award-info":[{"award-number":["DE-FG02-06ER54857"]}]},{"name":"ExaCT Combustion Co-Design Center","award":["4000110839"],"award-info":[{"award-number":["4000110839"]}]},{"name":"Rutgers Discovery Informatics Institute"},{"DOI":"10.13039\/100006234","name":"Sandia National Laboratories","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006234","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Technology and Engineering Solutions of Sandia"},{"name":"Honeywell International"},{"DOI":"10.13039\/100000015","name":"U.S. Department of Energy\u2019s","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000015","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006168","name":"National Nuclear Security Administration","doi-asserted-by":"publisher","award":["DE-NA0003525"],"award-info":[{"award-number":["DE-NA0003525"]}],"id":[{"id":"10.13039\/100006168","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Parallel Distrib. Syst."],"published-print":{"date-parts":[[2017,10,1]]},"DOI":"10.1109\/tpds.2017.2696538","type":"journal-article","created":{"date-parts":[[2017,4,24]],"date-time":"2017-04-24T18:07:13Z","timestamp":1493057233000},"page":"2881-2895","source":"Crossref","is-referenced-by-count":11,"title":["Modeling and Simulating Multiple Failure Masking Enabled by Local Recovery for Stencil-Based Applications at Extreme Scales"],"prefix":"10.1109","volume":"28","author":[{"given":"Marc","family":"Gamell","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Keita","family":"Teranishi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jackson","family":"Mayo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hemanth","family":"Kolla","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michael A.","family":"Heroux","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jacqueline","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Manish","family":"Parashar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ExaMPI.2014.6"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1137\/070693199"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICPP.2011.85"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICPP.2012.45"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2010.18"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/2063384.2063427"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER.2014.6968739"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/12.142678"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/62546.62575"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2012.77"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/2465813.2465814"},{"key":"ref40","first-page":"51:51","article-title":"Toward local failure local recovery resilience model using MPI-ULFM","author":"teranishi","year":"2014","journal-title":"Proceedings of the 21st European MPI Users' Group Meeting"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/2807591.2807672"},{"key":"ref12","first-page":"279","article-title":"Exploring failure recovery for stencil-based applications at extreme scales","author":"gamell","year":"2015","journal-title":"Proc Int Symp High-Perform Parallel Distrib Comput"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2003.1197125"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2007.370605"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/1551609.1551619"},{"key":"ref16","article-title":"Coordinated checkpoint\/restart process fault tolerance for MPI applications on HPC systems","author":"hursey","year":"2010"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/46\/1\/067"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/568522.568525"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTR.2003.1253321"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2013.69"},{"key":"ref4","first-page":"895","article-title":"Exploring automatic, online failure recovery for scientific applications at extreme scales","author":"gamell","year":"2014","journal-title":"Proc Int Conf High Perform Comput Netw Storage Anal"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/DSNW.2012.6264677"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/DSN.2014.101"},{"key":"ref6","article-title":"Exascale operating systems and runtime software report","author":"beckman","year":"2012","journal-title":"Tech Rep"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/SNAPI.2010.10"},{"key":"ref5","article-title":"Fault tolerance for extreme-scale computing workshop, albuquerque, NM - march 19-20, 2009","author":"katz","year":"2009","journal-title":"Tech Rep"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1177\/1094342006067469"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.2172\/1078029"},{"key":"ref2","article-title":"ExaScale software study: Software challenges in extreme scale systems","author":"amarasinghe","year":"2009"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.2172\/1081941"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1177\/1094342010391989"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/2807591.2807665"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/214451.214456"},{"key":"ref45","doi-asserted-by":"crossref","first-page":"125","DOI":"10.1007\/978-3-540-75416-9_22","article-title":"A Case for Standard Non-Blocking Collective Operations","author":"hoefler","year":"2007","journal-title":"Recent Advances in Parallel Virtual Machine and Message Passing Interface"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTR.2009.5289157"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/DSN.2015.52"},{"key":"ref21","first-page":"18","article-title":"Blocking versus non-blocking coordinated checkpointing for large-scale fault tolerant MPI","author":"coti","year":"2006","journal-title":"Proc Int Conf High Perform Comput Netw Storage Anal"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/0743-7315(88)90027-5"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2011.95"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TC.1984.1676475"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/2503210.2503271"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1088\/1749-4699\/2\/1\/015001"},{"key":"ref26","first-page":"93","article-title":"FTC-Charm++: An in-memory checkpoint-based fault tolerant runtime for Charm++ and MPI","author":"zheng","year":"2004","journal-title":"Proc IEEE Int Conf Cluster Comput"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/2145816.2145845"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/2493123.2462908"}],"container-title":["IEEE Transactions on Parallel and Distributed Systems"],"original-title":[],"link":[{"URL":"http:\/\/ieeexplore.ieee.org\/ielaam\/71\/8030254\/7908967-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/71\/8030254\/07908967.pdf?arnumber=7908967","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,8]],"date-time":"2022-04-08T18:48:43Z","timestamp":1649443723000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7908967\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,10,1]]},"references-count":47,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tpds.2017.2696538","relation":{},"ISSN":["1045-9219"],"issn-type":[{"value":"1045-9219","type":"print"}],"subject":[],"published":{"date-parts":[[2017,10,1]]}}}