{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,2]],"date-time":"2026-10-02T11:00:07Z","timestamp":1790938807429,"version":"4.1.0"},"publisher-location":"Berlin, Heidelberg","reference-count":17,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"value":"9783642328190","type":"print"},{"value":"9783642328206","type":"electronic"}],"license":[{"start":{"date-parts":[[2012,1,1]],"date-time":"2012-01-01T00:00:00Z","timestamp":1325376000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2012]]},"DOI":"10.1007\/978-3-642-32820-6_48","type":"book-chapter","created":{"date-parts":[[2012,8,23]],"date-time":"2012-08-23T12:26:25Z","timestamp":1345724785000},"page":"477-488","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":17,"title":["A Checkpoint-on-Failure Protocol for Algorithm-Based Recovery in Standard MPI"],"prefix":"10.1007","author":[{"given":"Wesley","family":"Bland","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peng","family":"Du","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aurelien","family":"Bouteiller","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Thomas","family":"Herault","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"George","family":"Bosilca","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jack","family":"Dongarra","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","reference":[{"issue":"2","key":"48_CR1","first-page":"111","volume":"21","author":"F. Cappello","year":"2011","unstructured":"Cappello, F., Casanova, H., Robert, Y.: Preventive migration vs. preventive checkpointing for extreme scale supercomputers. PPL\u00a021(2), 111\u2013132 (2011)","journal-title":"PPL"},{"issue":"4","key":"48_CR2","first-page":"374","volume":"23","author":"F. Cappello","year":"2009","unstructured":"Cappello, F., Geist, A., Gropp, B., Kal\u00e9, L.V., Kramer, B., Snir, M.: Toward exascale resilience. IJHPCA\u00a023(4), 374\u2013388 (2009)","journal-title":"IJHPCA"},{"key":"48_CR3","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1145\/1065944.1065973","volume-title":"Proceedings of the Tenth ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, PPoPP 2005","author":"Z. Chen","year":"2005","unstructured":"Chen, Z., Fagg, G.E., Gabriel, E., Langou, J., Angskun, T., Bosilca, G., Dongarra, J.: Fault tolerant high performance computing by a coding approach. In: Proceedings of the Tenth ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, PPoPP 2005, pp. 213\u2013223. ACM, New York (2005)"},{"key":"48_CR4","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1016\/j.future.2004.11.016","volume":"22","author":"J.T. Daly","year":"2006","unstructured":"Daly, J.T.: A higher order estimate of the optimum checkpoint interval for restart dumps. Future Gener. Comput. Syst.\u00a022, 303\u2013312 (2006)","journal-title":"Future Gener. Comput. Syst."},{"key":"48_CR5","doi-asserted-by":"crossref","unstructured":"Davies, T., Karlsson, C., Liu, H., Ding, C., Chen, Z.: High Performance Linpack Benchmark: A Fault Tolerant Implementation without Checkpointing. In: Proceedings of the 25th ACM International Conference on Supercomputing (ICS 2011). ACM (2011)","DOI":"10.1145\/1995896.1995923"},{"issue":"11","key":"48_CR6","first-page":"3","volume":"25","author":"J. Dongarra","year":"2011","unstructured":"Dongarra, J., Beckman, P., et al.: The international exascale software roadmap. IJHPCA\u00a025(11), 3\u201360 (2011)","journal-title":"IJHPCA"},{"key":"48_CR7","volume-title":"ScaLAPACK user\u2019s guide","author":"J.J. Dongarra","year":"1997","unstructured":"Dongarra, J.J., Blackford, L.S., Choi, J., et al.: ScaLAPACK user\u2019s guide. Society for Industrial and Applied Mathematics, Philadelphia (1997)"},{"key":"48_CR8","doi-asserted-by":"crossref","unstructured":"Du, P., Bouteiller, A., Bosilca, G., Herault, T., Dongarra, J.: Algorithm-based Fault Tolerance for Dense Matrix Factorizations. In: 17th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming. ACM (2012)","DOI":"10.1145\/2145816.2145845"},{"key":"48_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"346","DOI":"10.1007\/3-540-45255-9_47","volume-title":"Recent Advances in Parallel Virtual Machine and Message Passing Interface","author":"G.E. Fagg","year":"2000","unstructured":"Fagg, G.E., Dongarra, J.: FT-MPI: Fault Tolerant MPI, Supporting Dynamic Applications in a Dynamic World. In: Dongarra, J., Kacsuk, P., Podhorszki, N. (eds.) PVM\/MPI 2000. LNCS, vol.\u00a01908, p. 346. Springer, Heidelberg (2000)"},{"key":"48_CR10","doi-asserted-by":"publisher","first-page":"259","DOI":"10.1145\/322123.322131","volume":"26","author":"E. Gelenbe","year":"1979","unstructured":"Gelenbe, E.: On the optimum checkpoint interval. JoACM\u00a026, 259\u2013270 (1979)","journal-title":"JoACM"},{"key":"48_CR11","doi-asserted-by":"publisher","first-page":"363","DOI":"10.1177\/1094342004046045","volume":"18","author":"W. Gropp","year":"2004","unstructured":"Gropp, W., Lusk, E.: Fault tolerance in message passing interface programs. Int. J. High Perform. Comput. Appl.\u00a018, 363\u2013372 (2004)","journal-title":"Int. J. High Perform. Comput. Appl."},{"issue":"6","key":"48_CR12","doi-asserted-by":"publisher","first-page":"518","DOI":"10.1109\/TC.1984.1676475","volume":"100","author":"K.H. Huang","year":"1984","unstructured":"Huang, K.H., Abraham, J.A.: Algorithm-based fault tolerance for matrix operations. IEEE Transactions on Computers\u00a0100(6), 518\u2013528 (1984)","journal-title":"IEEE Transactions on Computers"},{"issue":"2","key":"48_CR13","doi-asserted-by":"publisher","first-page":"172","DOI":"10.1016\/0743-7315(88)90027-5","volume":"5","author":"F.T. Luk","year":"1988","unstructured":"Luk, F.T., Park, H.: An analysis of algorithm-based fault tolerance techniques. Journal of Parallel and Distributed Computing\u00a05(2), 172\u2013184 (1988)","journal-title":"Journal of Parallel and Distributed Computing"},{"key":"48_CR14","first-page":"1590","volume":"61","author":"J.S. Plank","year":"2001","unstructured":"Plank, J.S., Thomason, M.G.: Processor allocation and checkpoint interval selection in cluster computing systems. JPDC\u00a061, 1590 (2001)","journal-title":"JPDC"},{"key":"48_CR15","doi-asserted-by":"crossref","unstructured":"Schroeder, B., Gibson, G.A.: Understanding Failures in Petascale Computers. SciDAC, Journal of Physics: Conference Series\u00a078 (2007)","DOI":"10.1088\/1742-6596\/78\/1\/012022"},{"key":"48_CR16","unstructured":"The MPI Forum. MPI: A Message-Passing Interface Standard, Version 2.2. Technical report (2009)"},{"key":"48_CR17","doi-asserted-by":"publisher","first-page":"530","DOI":"10.1145\/361147.361115","volume":"17","author":"J.W. Young","year":"1974","unstructured":"Young, J.W.: A first order approximation to the optimum checkpoint interval. Commun. ACM\u00a017, 530\u2013531 (1974)","journal-title":"Commun. ACM"}],"container-title":["Lecture Notes in Computer Science","Euro-Par 2012 Parallel Processing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-32820-6_48","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,4,20]],"date-time":"2020-04-20T00:55:08Z","timestamp":1587344108000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-32820-6_48"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012]]},"ISBN":["9783642328190","9783642328206"],"references-count":17,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-32820-6_48","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2012]]},"assertion":[{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}