{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T19:46:45Z","timestamp":1771703205019,"version":"3.50.1"},"reference-count":28,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2012,6]]},"DOI":"10.1109\/dsnw.2012.6264668","type":"proceedings-article","created":{"date-parts":[[2012,8,17]],"date-time":"2012-08-17T15:49:12Z","timestamp":1345218552000},"page":"1-6","source":"Crossref","is-referenced-by-count":2,"title":["Asynchronous checkpoint migration with MRNet in the Scalable Checkpoint \/ Restart Library"],"prefix":"10.1109","author":[{"given":"Kathryn","family":"Mohror","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Adam","family":"Moody","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bronis R.","family":"de Supinski","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"19","article-title":"A composable runtime recovery policy framework supporting resilient HPC applications","author":"hursey","year":"2010","journal-title":"Indiana University Tech Rep TR686"},{"key":"17","doi-asserted-by":"publisher","DOI":"10.1109\/ICPP.2011.85"},{"key":"18","article-title":"FTI: High performance fault tolerance interface for hybrid systems","author":"bautista-gomez","year":"2011","journal-title":"Proc Int Conf High-Performance Computing"},{"key":"15","doi-asserted-by":"publisher","DOI":"10.1145\/1654059.1654117"},{"key":"16","doi-asserted-by":"publisher","DOI":"10.1109\/88.311574"},{"key":"13","first-page":"213","article-title":"Fault tolerant high performance computing by a coding approach","author":"chen","year":"2005","journal-title":"Proceedings of the ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming PPOPP"},{"key":"14","first-page":"63","article-title":"Distributed diskless checkpoint for large scale systems","author":"bautista-gomez","year":"2010","journal-title":"CC-GRID"},{"key":"11","doi-asserted-by":"publisher","DOI":"10.1145\/1048935.1050172"},{"key":"12","doi-asserted-by":"publisher","DOI":"10.1109\/71.730527"},{"key":"21","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTR.2009.5289188"},{"key":"20","doi-asserted-by":"publisher","DOI":"10.1145\/1551609.1551618"},{"key":"22","article-title":"Can checkpoint\/Restart mechanisms benefit from hierarchical data staging?","author":"rajachandrasekar","year":"2011","journal-title":"Proceedings of the Workshop on Resiliency in High Performance Computing in Clusters"},{"key":"23","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2007.370254"},{"key":"24","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTR.2008.4663757"},{"key":"25","year":"0","journal-title":"LaunchMON"},{"key":"26","year":"0","journal-title":"LLNL LC Parallel File Systems Summary"},{"key":"27","year":"0","journal-title":"IOR Benchmark"},{"key":"28","year":"0"},{"key":"3","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/78\/1\/012022"},{"key":"2","doi-asserted-by":"publisher","DOI":"10.1109\/TDMR.2005.855685"},{"key":"1","doi-asserted-by":"publisher","DOI":"10.1109\/DSN.2006.5"},{"key":"10","article-title":"A case for multi-level distributed recovery schemes","author":"vaidya","year":"1994","journal-title":"Texas A & M University Tech Rep 94-043"},{"key":"7","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2010.18"},{"key":"6","article-title":"Parallel I\/O on the IBM blue gene\/L system","author":"ross","year":"2006","journal-title":"Blue Gene\/L Consortium Quarterly Newsletter Tech Rep"},{"key":"5","first-page":"153","article-title":"ZOID: I\/O-forwarding infrastructure for petascale architectures","author":"iskra","year":"2008","journal-title":"PPoPP '08 Proceedings of the 13th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming"},{"key":"4","author":"sarkar","year":"2009","journal-title":"ExaScale Software Study Software Challenges in Exascale Systems"},{"key":"9","first-page":"251","article-title":"A model of roll-back recovery with multiple checkpoints","author":"gelenbe","year":"1976","journal-title":"Proceedings of the 2nd International Conference on Software Engineering (ICSE '76)"},{"key":"8","year":"0","journal-title":"Scalable Checkpoint\/Restart Library"}],"event":{"name":"2012 IEEE\/IFIP 42nd International Conference on Dependable Systems and Networks Workshops (DSN-W)","location":"Boston, MA, USA","start":{"date-parts":[[2012,6,25]]},"end":{"date-parts":[[2012,6,28]]}},"container-title":["IEEE\/IFIP International Conference on Dependable Systems and Networks Workshops (DSN 2012)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/6255871\/6264647\/06264668.pdf?arnumber=6264668","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,3,21]],"date-time":"2017-03-21T20:35:10Z","timestamp":1490128510000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6264668\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012,6]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/dsnw.2012.6264668","relation":{},"subject":[],"published":{"date-parts":[[2012,6]]}}}