{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T18:30:05Z","timestamp":1791916205607,"version":"4.3.4"},"reference-count":56,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2018,10,1]],"date-time":"2018-10-01T00:00:00Z","timestamp":1538352000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2018,10,1]],"date-time":"2018-10-01T00:00:00Z","timestamp":1538352000000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2018,10,1]],"date-time":"2018-10-01T00:00:00Z","timestamp":1538352000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2018,10,1]],"date-time":"2018-10-01T00:00:00Z","timestamp":1538352000000},"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","doi-asserted-by":"publisher","award":["CCF-1252500"],"award-info":[{"award-number":["CCF-1252500"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CCF-1302693"],"award-info":[{"award-number":["CCF-1302693"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Sustain. Comput."],"published-print":{"date-parts":[[2018,10,1]]},"DOI":"10.1109\/tsusc.2018.2797890","type":"journal-article","created":{"date-parts":[[2018,1,24]],"date-time":"2018-01-24T19:19:06Z","timestamp":1516821546000},"page":"332-345","source":"Crossref","is-referenced-by-count":6,"title":["Resilience-Aware Resource Management for Exascale Computing Systems"],"prefix":"10.1109","volume":"3","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6858-8221","authenticated-orcid":false,"given":"Daniel","family":"Dauwe","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0846-0066","authenticated-orcid":false,"given":"Sudeep","family":"Pasricha","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1376-5825","authenticated-orcid":false,"given":"Anthony A.","family":"Maciejewski","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Howard Jay","family":"Siegel","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2001.925102"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.parco.2008.11.001"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/1272366.1272381"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2010.151"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/BF00383389"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ISORC.2005.39"},{"key":"ref37","doi-asserted-by":"crossref","first-page":"941","DOI":"10.1016\/j.jpdc.2010.05.002","article-title":"Reliability-aware scheduling strategy\n for heterogeneous distributed computing systems","volume":"70","author":"tang","year":"2010","journal-title":"J Parallel Distrib Comput"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2014.2360513"},{"key":"ref35","first-page":"1","article-title":"Utility-based resource management in an oversubscribede\n energy-constrained heterogeneous environment executing parallel applications","author":"machovec","year":"2017","journal-title":"Parallel Comput"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.suscom.2014.08.001"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2014.2360536"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-54420-0_67"},{"key":"ref29","first-page":"112","article-title":"A\n time-driven scheduling model for real-time operating systems.","volume":"85","author":"jensen","year":"1985","journal-title":"Proc Real-Time Syst Symp"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/DSN.2015.50"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1177\/1094342009106189"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2014.122"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2016.2643660"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2016.2546248"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/62546.62575"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/214451.214456"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/PROC.1976.10239"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.parco.2014.03.005"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1002\/9780470117880"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/DSN.2014.62"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/11556930_25"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2011.133"},{"key":"ref54","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 Int Conf Cluster Comput"},{"key":"ref53","article-title":"Resource management for extreme scale high performance computing\n systems in the presence of failures","author":"dauwe","year":"2018"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/NAS.2016.7549410"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-013-0884-0"},{"key":"ref11","first-page":"9","article-title":"A discussion of checkpoint restart","volume":"3","author":"jasper","year":"1969","journal-title":"Software Agent"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/71.735960"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/361147.361115"},{"key":"ref13","first-page":"1","article-title":"Blocking\n versus non-blocking coordinated checkpointing for large-scale fault tolerant MPI","author":"coti","year":"2006","journal-title":"Proc Conf Supercomputing"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER.2012.82"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2011.95"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/223587.223596"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/2063384.2063427"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2013.100"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CCGRID.2010.40"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.2172\/984082"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2014.2342228"},{"key":"ref6","first-page":"5","article-title":"Toward exascale resilience: 2014 update","volume":"1","author":"cappello","year":"2014","journal-title":"Supercomputing Frontiers and Innovations"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS.2012.56"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CIT.2016.44"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2012.55"},{"key":"ref49","article-title":"DDR4 SDRAM standard","author":"association","year":"2017"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW.2017.41"},{"key":"ref46","year":"2016"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-016-1783-y"},{"key":"ref48","year":"2017"},{"key":"ref47","article-title":"Report on the Sunway Taihulight System","author":"dongarra","year":"2016"},{"key":"ref42","doi-asserted-by":"crossref","first-page":"282","DOI":"10.1016\/j.jpdc.2008.11.007","article-title":"On the design of communication-aware fault-tolerant scheduling algorithms for precedence\n constrained tasks in grid computing systems with dedicated communication devices","volume":"69","author":"zheng","year":"2009","journal-title":"J Parall Distrib Comput"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.parco.2006.06.006"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICPP.2016.21"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTR.2007.4629245"}],"container-title":["IEEE Transactions on Sustainable Computing"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielaam\/7274860\/8568955\/8268650-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7274860\/8568955\/08268650.pdf?arnumber=8268650","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,8]],"date-time":"2022-04-08T18:54:56Z","timestamp":1649444096000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8268650\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,10,1]]},"references-count":56,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tsusc.2018.2797890","relation":{},"ISSN":["2377-3782","2377-3790"],"issn-type":[{"value":"2377-3782","type":"electronic"},{"value":"2377-3790","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,10,1]]}}}