{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T14:43:21Z","timestamp":1742913801083,"version":"3.40.3"},"publisher-location":"Cham","reference-count":12,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030105488"},{"type":"electronic","value":"9783030105495"}],"license":[{"start":{"date-parts":[[2018,12,31]],"date-time":"2018-12-31T00:00:00Z","timestamp":1546214400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2018,12,31]],"date-time":"2018-12-31T00:00:00Z","timestamp":1546214400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019]]},"DOI":"10.1007\/978-3-030-10549-5_63","type":"book-chapter","created":{"date-parts":[[2018,12,31]],"date-time":"2018-12-31T00:03:31Z","timestamp":1546214611000},"page":"813-825","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Performance Efficient Multiresilience Using Checkpoint Recovery in Iterative Algorithms"],"prefix":"10.1007","author":[{"given":"Rizwan A.","family":"Ashraf","sequence":"first","affiliation":[]},{"given":"Christian","family":"Engelmann","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,12,31]]},"reference":[{"key":"63_CR1","doi-asserted-by":"crossref","unstructured":"Ashraf, R.A., Hukerikar, S., Engelmann, C.: Pattern-based modeling of multiresilience solutions for high-performance computing. In: Proceedings of the 2018 ACM\/SPEC International Conference on Performance Engineering (2018)","DOI":"10.1145\/3184407.3184421"},{"key":"63_CR2","doi-asserted-by":"crossref","unstructured":"Benoit, A., Cavelan, A., Robert, Y., Sun, H.: Optimal resilience patterns to cope with fail-stop and silent errors. Report RR-8786, LIP - ENS Lyon (October 2015)","DOI":"10.1109\/IPDPS.2016.39"},{"issue":"3","key":"63_CR3","doi-asserted-by":"publisher","first-page":"244","DOI":"10.1177\/1094342013488238","volume":"27","author":"W Bland","year":"2013","unstructured":"Bland, W., Bouteiller, A., Herault, T., Bosilca, G., Dongarra, J.: Post-failure recovery of MPI communication capability. Int. J. High Perform. Comput. Appl. 27(3), 244\u2013254 (2013)","journal-title":"Int. J. High Perform. Comput. Appl."},{"key":"63_CR4","doi-asserted-by":"crossref","unstructured":"Bronevetsky, G., de Supinski, B.: Soft error vulnerability of iterative linear algebra methods. In: 22nd Annual International Conference on Supercomputing (2008)","DOI":"10.1145\/1375527.1375552"},{"key":"63_CR5","doi-asserted-by":"crossref","unstructured":"Cao, J., Arya, K., Garg, R., Matott, S., Panda, D.K., Subramoni, H., Vienne, J., Cooperman, G.: System-level scalable checkpoint-restart for petascale computing. In: IEEE 22nd International Conference on Parallel and Distributed Systems (2016)","DOI":"10.1109\/ICPADS.2016.0125"},{"key":"63_CR6","doi-asserted-by":"crossref","unstructured":"Chen, Z.: Algorithm-based recovery for iterative methods without checkpointing. In: 20th International Symposium on High Performance Distributed Computing (2011)","DOI":"10.1145\/1996130.1996142"},{"issue":"3","key":"63_CR7","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1016\/j.future.2004.11.016","volume":"22","author":"J Daly","year":"2006","unstructured":"Daly, J.: A higher order estimate of the optimum checkpoint interval for restart dumps. Futur. Gener. Comput. Syst. 22(3), 303\u2013312 (2006)","journal-title":"Futur. Gener. Comput. Syst."},{"key":"63_CR8","doi-asserted-by":"crossref","unstructured":"Elliott, J., Hoemmen, M., Mueller, F.: Evaluating the impact of SDC on the GMRES iterative solver. In: 2014 IEEE 28th International Parallel and Distributed Processing Symposium, pp. 1193\u20131202 (May 2014)","DOI":"10.1109\/IPDPS.2014.123"},{"key":"63_CR9","doi-asserted-by":"crossref","unstructured":"Hukerikar, S., Engelmann, C.: Resilience design patterns: a structured approach to resilience at extreme scale (version 1.2). Technical report ORNL\/TM-2017\/745, Oak Ridge National Laboratory, Oak Ridge, TN, USA (August 2017)","DOI":"10.2172\/1436045"},{"key":"63_CR10","doi-asserted-by":"crossref","unstructured":"Jaulmes, L., Casas, M., Moret\u00f3, M., Ayguad\u00e9, E., Labarta, J., Valero, M.: Exploiting asynchrony from exact forward recovery for DUE in iterative solvers. In: International Conference for High Performance Computing, Networking, Storage and Analysis (2015)","DOI":"10.1145\/2807591.2807599"},{"key":"63_CR11","doi-asserted-by":"crossref","unstructured":"Sloan, J., Kumar, R., Bronevetsky, G.: An algorithmic approach to error localization and partial recomputation for low-overhead fault tolerance. In: 43rd Annual IEEE\/IFIP International Conference on Dependable Systems and Networks (2013)","DOI":"10.1109\/DSN.2013.6575309"},{"key":"63_CR12","unstructured":"Zheng, G., Shi, L., Kale, L.V.: FTC-Charm++: an in-memory checkpoint-based fault tolerant runtime for Charm++ and MPI. In: 2004 IEEE International Conference on Cluster Computing, pp. 93\u2013103 (September 2004)"}],"container-title":["Lecture Notes in Computer Science","Euro-Par 2018: Parallel Processing Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-10549-5_63","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T08:45:05Z","timestamp":1672562705000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-10549-5_63"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,12,31]]},"ISBN":["9783030105488","9783030105495"],"references-count":12,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-10549-5_63","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2018,12,31]]},"assertion":[{"value":"31 December 2018","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"Euro-Par","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Parallel Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Turin","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 August 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31 August 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"europar2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/europar2018.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}