{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T04:08:47Z","timestamp":1750306127662,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":20,"publisher":"ACM","license":[{"start":{"date-parts":[[2017,6,26]],"date-time":"2017-06-26T00:00:00Z","timestamp":1498435200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2017,6,26]]},"DOI":"10.1145\/3086157.3086165","type":"proceedings-article","created":{"date-parts":[[2017,6,23]],"date-time":"2017-06-23T12:46:51Z","timestamp":1498222011000},"page":"9-16","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Optimal Checkpointing Period with Replicated Execution on Heterogeneous Platforms"],"prefix":"10.1145","author":[{"given":"Anne","family":"Benoit","sequence":"first","affiliation":[{"name":"LIP, ENS Lyon, Lyon, France"}]},{"given":"Aur\u00e9lien","family":"Cavelan","sequence":"additional","affiliation":[{"name":"LIP, ENS Lyon, Lyon, France"}]},{"given":"Valentin","family":"Le F\u00e8vre","sequence":"additional","affiliation":[{"name":"LIP, ENS Lyon, Lyon, France"}]},{"given":"Yves","family":"Robert","sequence":"additional","affiliation":[{"name":"LIP, ENS Lyon & University of Tennessee, Knoxville, Lyon, France"}]}],"member":"320","published-online":{"date-parts":[[2017,6,26]]},"reference":[{"volume-title":"Top500 Supercomputer Sites. (November","year":"2016","key":"e_1_3_2_1_1_1","unstructured":"2016. Top500 Supercomputer Sites. (November 2016 ). https:\/\/www.top500.org\/ lists\/2016\/11\/. 2016. Top500 Supercomputer Sites. (November 2016). https:\/\/www.top500.org\/ lists\/2016\/11\/."},{"key":"e_1_3_2_1_2_1","volume-title":"Valentin Le F'evre, and Yves Robert","author":"Benoit Anne","year":"2017","unstructured":"Anne Benoit , Aur\u00e9lien Cavelan , Valentin Le F'evre, and Yves Robert . 2017 . Optimal checkpointing period with replicated execution on heterogeneous platforms. Research report RR-9047. INRIA. Anne Benoit, Aur\u00e9lien Cavelan, Valentin Le F'evre, and Yves Robert. 2017. Optimal checkpointing period with replicated execution on heterogeneous platforms. Research report RR-9047. INRIA."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.14529\/jsfi140101"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1177\/1094342013505348"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2004.11.016"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2014.122"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2016.2546248"},{"key":"e_1_3_2_1_8_1","unstructured":"C. Engelmann H. H. Ong and S. L. Scorr. 2009. The case for modular redundancy in large-scale highh performance computing systems. In PDCN. IASTED.  C. Engelmann H. H. Ong and S. L. Scorr. 2009. The case for modular redundancy in large-scale highh performance computing systems. In PDCN. IASTED."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/2063384.2063443"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"crossref","unstructured":"Thomas H\u00e9rault and Yves Robert (Eds.). 2015. Fault-Tolerance Techniques for High-Performance Computing. Springer Verlag.   Thomas H\u00e9rault and Yves Robert (Eds.). 2015. Fault-Tolerance Techniques for High-Performance Computing. Springer Verlag.","DOI":"10.1007\/978-3-319-20943-2"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-03770-2_19"},{"volume-title":"Int. Conf. on Computing, Networking and Communications (ICNC). IEEE, 73--77","author":"Mills B.","key":"e_1_3_2_1_12_1","unstructured":"B. Mills , T. Znati , and R. Melhem . 2014. Shadow Computing: An energy-aware fault tolerant computing model . In Int. Conf. on Computing, Networking and Communications (ICNC). IEEE, 73--77 . B. Mills, T. Znati, and R. Melhem. 2014. Shadow Computing: An energy-aware fault tolerant computing model. In Int. Conf. on Computing, Networking and Communications (ICNC). IEEE, 73--77."},{"volume-title":"Probability and Computing: Randomized Algorithms and Probabilistic Analysis","author":"Mitzenmacher Michael","key":"e_1_3_2_1_13_1","unstructured":"Michael Mitzenmacher and Eli Upfal . 2005. Probability and Computing: Randomized Algorithms and Probabilistic Analysis . Cambridge University Press . Michael Mitzenmacher and Eli Upfal. 2005. Probability and Computing: Randomized Algorithms and Probabilistic Analysis. Cambridge University Press."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2010.18"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/71.920586"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/78\/1\/012022"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1177\/1094342014522573"},{"volume-title":"Using Replication and Checkpointing for Reliable Task Management in Computational Grids. In SC'10","author":"Yi S.","key":"e_1_3_2_1_18_1","unstructured":"S. Yi , D. Kondo , B. Kim , G. Park , and Y. Cho . 2010 . Using Replication and Checkpointing for Reliable Task Management in Computational Grids. In SC'10 . ACM. S. Yi, D. Kondo, B. Kim, G. Park, and Y. Cho. 2010. Using Replication and Checkpointing for Reliable Task Management in Computational Grids. In SC'10. ACM."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/361147.361115"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"crossref","unstructured":"Z. Zheng and Z. Lan. 2009. Reliability-aware scalability models for high performance computing. In Cluster Computing. IEEE.  Z. Zheng and Z. Lan. 2009. Reliability-aware scalability models for high performance computing. In Cluster Computing. IEEE.","DOI":"10.1109\/CLUSTR.2009.5289177"}],"event":{"name":"HPDC '17: The 26th International Symposium on High-Performance Parallel and Distributed Computing","sponsor":["University of Arizona University of Arizona","SIGARCH ACM Special Interest Group on Computer Architecture","SIGHPC ACM Special Interest Group on High Performance Computing, Special Interest Group on High Performance Computing"],"location":"Washington DC USA","acronym":"HPDC '17"},"container-title":["Proceedings of the 2017 Workshop on Fault-Tolerance for HPC at Extreme Scale"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3086157.3086165","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3086157.3086165","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T03:37:01Z","timestamp":1750217821000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3086157.3086165"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,6,26]]},"references-count":20,"alternative-id":["10.1145\/3086157.3086165","10.1145\/3086157"],"URL":"https:\/\/doi.org\/10.1145\/3086157.3086165","relation":{},"subject":[],"published":{"date-parts":[[2017,6,26]]},"assertion":[{"value":"2017-06-26","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}