{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T12:16:35Z","timestamp":1763468195468,"version":"3.37.3"},"reference-count":43,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2015,7,1]],"date-time":"2015-07-01T00:00:00Z","timestamp":1435708800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"DOI":"10.13039\/100000015","name":"Department of Energy","doi-asserted-by":"publisher","award":["DOE DE-SC0001845"],"award-info":[{"award-number":["DOE DE-SC0001845"]}],"id":[{"id":"10.13039\/100000015","id-type":"DOI","asserted-by":"publisher"}]},{"name":"XSEDE","award":["ASC050039N"],"award-info":[{"award-number":["ASC050039N"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Parallel Distrib. Syst."],"published-print":{"date-parts":[[2015,7,1]]},"DOI":"10.1109\/tpds.2014.2342228","type":"journal-article","created":{"date-parts":[[2014,7,23]],"date-time":"2014-07-23T16:10:15Z","timestamp":1406131815000},"page":"2061-2074","source":"Crossref","is-referenced-by-count":23,"title":["Using Migratable Objects to Enhance Fault Tolerance Schemes in Supercomputers"],"prefix":"10.1109","volume":"26","author":[{"given":"Esteban","family":"Meneses","sequence":"first","affiliation":[]},{"given":"Xiang","family":"Ni","sequence":"additional","affiliation":[]},{"given":"Gengbin","family":"Zheng","sequence":"additional","affiliation":[]},{"given":"Celso L.","family":"Mendes","sequence":"additional","affiliation":[]},{"given":"Laxmikant V.","family":"Kale","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1142\/S0129626411000126"},{"key":"ref38","first-page":"40:1","article-title":"Optimized pre-copy live migration for memory intensive applications","author":"ibrahim","year":"2011","journal-title":"Proc 2011 Int Conf High Perform Comput Netw Storage Anal"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/DSN.2006.5"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2004.11.016"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/361147.361115"},{"article-title":"The NAS parallel benchmarks","year":"1994","author":"bailey","key":"ref30"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER.2010.20"},{"key":"ref36","first-page":"1","article-title":"Proactive process-level live migration in HPC environments","author":"wang","year":"2008","journal-title":"Proc Int Conf High Perform Comput Netw Storage Anal"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/IPPS.1996.508106"},{"key":"ref34","doi-asserted-by":"crossref","first-page":"630","DOI":"10.1016\/j.jpdc.2010.03.003","article-title":"A study of dynamic meta-learning for failure prediction in large-scale systems","volume":"70","author":"lan","year":"2010","journal-title":"J Parallel Distrib Comput"},{"key":"ref10","article-title":"Proactive fault tolerance in large systems","author":"chakravorty","year":"2005","journal-title":"Proc of HPCRI Workshop in conjunction with HPCA"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2008.90"},{"key":"ref11","first-page":"485","article-title":"Proactive fault tolerance in MPI applications via task migration","volume":"4297","author":"chakravorty","year":"2006","journal-title":"Proc 13th Int Conf High Perform Comput"},{"key":"ref12","first-page":"496","article-title":"An efficient and transparent thread migration scheme in the $PM^2$ runtime system","author":"antoniu","year":"1999","journal-title":"Proc 3rd Workshop Runtime Syst Parallel Program"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/214451.214456"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2007.02.002"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER.2012.82"},{"key":"ref16","first-page":"264","article-title":"Checkpointing","author":"schulz","year":"2011","journal-title":"Encyclopedia of Parallel Computing"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/46\/1\/067"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2010.18"},{"key":"ref19","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":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2007.370310"},{"key":"ref4","first-page":"91","article-title":"Charm++ : A portable concurrent object oriented system based on C++","author":"kal\u00e9","year":"1993","journal-title":"Proc Conf Object-Oriented Program Syst Lang Appl"},{"article-title":"Scalable message-logging techniques for effective fault tolerance in HPC applications","year":"2013","author":"meneses","key":"ref27"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1177\/1094342009106189"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/1362622.1362678"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2002.10019"},{"key":"ref5","first-page":"306","article-title":"Adaptive MPI","author":"huang","year":"2003","journal-title":"Proc 16th Int Workshop Lang Compilers Parallel Comput"},{"key":"ref8","doi-asserted-by":"crossref","first-page":"630","DOI":"10.1016\/j.jpdc.2010.03.003","article-title":"A study of dynamic meta-learning for failure prediction in large-scale systems","volume":"70","author":"lan","year":"2010","journal-title":"J Parallel Distrib Comput"},{"key":"ref7","first-page":"77:1","article-title":"Fault prediction under the microscope: A closer look into HPC systems","author":"gainaru","year":"2012","journal-title":"Proc Int Conf High Perform Comput Netw Storage Anal"},{"article-title":"Exascale computing study: Technology challenges in achieving exascale systems","year":"2008","author":"kogge","key":"ref2"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.665"},{"year":"0","key":"ref1"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/DSNW.2012.6264677"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/DSNW.2012.6264673"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/71.730527"},{"key":"ref42","first-page":"1","article-title":"FTI: High performance fault tolerance interface for hybrid systems","author":"bautista-gomez","year":"2011","journal-title":"Proc ACM Int Conf Supercomput"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3959.3962"},{"key":"ref41","first-page":"44:1","article-title":"Evaluating the viability of process replication reliability for exascale systems","author":"ferreira","year":"2011","journal-title":"Proc Int Conf High Perform Comput Netw Storage Anal"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/SBAC-PAD.2012.12"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2011.307"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCCN.2010.5560143"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS.1995.500024"}],"container-title":["IEEE Transactions on Parallel and Distributed Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/71\/7121064\/06862914.pdf?arnumber=6862914","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T11:40:56Z","timestamp":1641987656000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6862914\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,7,1]]},"references-count":43,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tpds.2014.2342228","relation":{},"ISSN":["1045-9219"],"issn-type":[{"type":"print","value":"1045-9219"}],"subject":[],"published":{"date-parts":[[2015,7,1]]}}}