{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,6]],"date-time":"2026-10-06T16:10:58Z","timestamp":1791303058898,"version":"4.1.0"},"reference-count":60,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2015,5,1]],"date-time":"2015-05-01T00:00:00Z","timestamp":1430438400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2015,5,1]],"date-time":"2015-05-01T00:00:00Z","timestamp":1430438400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2015,5,1]],"date-time":"2015-05-01T00:00:00Z","timestamp":1430438400000},"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":["CNS-0834514"],"award-info":[{"award-number":["CNS-0834514"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Comput."],"published-print":{"date-parts":[[2015,5,1]]},"DOI":"10.1109\/tc.2014.2317182","type":"journal-article","created":{"date-parts":[[2014,4,15]],"date-time":"2014-04-15T18:04:12Z","timestamp":1397585052000},"page":"1402-1415","source":"Crossref","is-referenced-by-count":10,"title":["Reliability-Aware Speedup Models for Parallel Applications with Coordinated Checkpointing\/Restart"],"prefix":"10.1109","volume":"64","author":[{"given":"Ziming","family":"Zheng","sequence":"first","affiliation":[{"name":"Department of Computer Science, Chicago, IL 60616"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Li","family":"Yu","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Chicago, IL 60616"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiling","family":"Lan","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Chicago, IL 60616"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2007.04.015"},{"key":"ref38","year":"0"},{"key":"ref33","first-page":"217","article-title":"A fast recovery mechanism for checkpointing\n in networked environments","author":"li","year":"0","journal-title":"Proc Int Conf Dependable Syst Netw"},{"key":"ref32","author":"nicola","year":"1995","journal-title":"Checkpointing and Modelling of Program Execution Time Software Fault Tolerance"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2004.1303239"},{"key":"ref30","article-title":"Investigating lightweight storage and\n overlay networks for fault tolerance","author":"oldfield","year":"0","journal-title":"Proc High Avail Perform Comput Workshop"},{"key":"ref37","article-title":"Exascale software study: Software\n challenges in extreme scale systems","author":"amarasinghe","year":"0"},{"key":"ref36","first-page":"795","article-title":"Application MTFE vs platform MTBF: A\n fresh perspective on system reliabilty and application throughput for computations at scale","author":"daly","year":"0","journal-title":"Proc IEEE Int Symp Cluster Comput Grid"},{"key":"ref35","year":"0"},{"key":"ref34","first-page":"43:1","article-title":"Proactive process-level live migration in\n HPC environments","author":"wang","year":"0","journal-title":"Proc Supercomput"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/2503210.2503271"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2008.494"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/109025.109118"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/1183401.1183406"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/DSN.2006.5"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/DSN.2007.103"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTR.2009.5289177"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/361147.361115"},{"key":"ref21","article-title":"Reliability aware optimal k node of\n parallel applications in large scale HPC systems","author":"gottumukkala","year":"0","journal-title":"Proc High Availability Perform Comput Workshop"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2005.337"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/11407522_13"},{"key":"ref26","first-page":"115","article-title":"Improved message logging versus\n improved coordinated checkpointing for fault tolerant MPI","author":"bouteiller","year":"0","journal-title":"Proc Int Conf Cluster Comput"},{"key":"ref25","year":"0"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/1654059.1654100"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2011.83"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1016\/S0304-3975(02)00566-2"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2012.18"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.2172\/984082"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2011.95"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/DSN.2012.6263948"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTR.2009.5289177"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/2063384.2063428"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/2063384.2063443"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2007.370246"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/1362622.1362687"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TR.2009.2034291"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2004.11.016"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/233013.233050"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1006\/jpdc.2001.1757"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/FTCS.1998.689454"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TDSC.2004.15"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/DSN.2005.67"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2008.90"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICPP.2008.17"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/42411.42415"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/1465482.1465560"},{"key":"ref6","year":"0"},{"key":"ref5","article-title":"Adaptive grid-enabled SIMOX\n simulation on Japan-US grid testbed","author":"tanaka","year":"0","journal-title":"Proc TeraGrid"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/24.58720"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/S0927-5452(04)80089-3"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1201\/9781420087444"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/SUPERC.1990.130037"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2009.03.007"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICPP.2010.80"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/MSST.2007.4367962"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICPPW.2009.42"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/71.862209"},{"key":"ref41","first-page":"1","article-title":"An optimal checkpoint\/restart model for a\n large scale high performance computing system","author":"liu","year":"0","journal-title":"Proc IEEE Int Symp Parallel Distrib Process"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ARES.2009.105"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/1851476.1851509"}],"container-title":["IEEE Transactions on Computers"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/12\/7079452\/06798722.pdf?arnumber=6798722","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,15]],"date-time":"2022-06-15T14:52:21Z","timestamp":1655304741000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/6798722\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,5,1]]},"references-count":60,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tc.2014.2317182","relation":{},"ISSN":["0018-9340","1557-9956","2326-3814"],"issn-type":[{"value":"0018-9340","type":"print"},{"value":"1557-9956","type":"electronic"},{"value":"2326-3814","type":"electronic"}],"subject":[],"published":{"date-parts":[[2015,5,1]]}}}