{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T20:47:24Z","timestamp":1725742044141},"publisher-location":"Berlin, Heidelberg","reference-count":19,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642400469"},{"type":"electronic","value":"9783642400476"}],"license":[{"start":{"date-parts":[[2013,1,1]],"date-time":"2013-01-01T00:00:00Z","timestamp":1356998400000},"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":[[2013]]},"DOI":"10.1007\/978-3-642-40047-6_43","type":"book-chapter","created":{"date-parts":[[2013,7,20]],"date-time":"2013-07-20T08:18:02Z","timestamp":1374308282000},"page":"420-431","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Multi-criteria Checkpointing Strategies: Response-Time versus Resource Utilization"],"prefix":"10.1007","author":[{"given":"Aurelien","family":"Bouteiller","sequence":"first","affiliation":[]},{"given":"Franck","family":"Cappello","sequence":"additional","affiliation":[]},{"given":"Jack","family":"Dongarra","sequence":"additional","affiliation":[]},{"given":"Amina","family":"Guermouche","sequence":"additional","affiliation":[]},{"given":"Thomas","family":"H\u00e9rault","sequence":"additional","affiliation":[]},{"given":"Yves","family":"Robert","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"issue":"4","key":"43_CR1","first-page":"309","volume":"23","author":"J. Dongarra","year":"2009","unstructured":"Dongarra, J., Beckman, P., Aerts, P., Cappello, F., Lippert, T., Matsuoka, S., Messina, P., Moore, T., Stevens, R., Trefethen, A., Valero, M.: The international exascale software project: a call to cooperative action by the global high-performance community. IJHPCA\u00a023(4), 309\u2013322 (2009)","journal-title":"IJHPCA"},{"key":"43_CR2","doi-asserted-by":"publisher","first-page":"12022","DOI":"10.1088\/1742-6596\/78\/1\/012022","volume":"78","author":"G. Gibson","year":"2007","unstructured":"Gibson, G.: Failure tolerance in petascale computers. Journal of Physics: Conference Series\u00a078, 012022 (2007)","journal-title":"Journal of Physics: Conference Series"},{"key":"43_CR3","doi-asserted-by":"crossref","unstructured":"Ferreira, K., Stearley, J., Laros, J.H.I., Oldfield, R., Pedretti, K., Brightwell, R., Riesen, R., Bridges, P.G., Arnold, D.: Evaluating the Viability of Process Replication Reliability for Exascale Systems. In: Proc. of SC 2011. ACM\/IEEE (2011)","DOI":"10.1145\/2063384.2063443"},{"key":"43_CR4","doi-asserted-by":"publisher","first-page":"375","DOI":"10.1145\/568522.568525","volume":"34","author":"E.N.M. Elnozahy","year":"2002","unstructured":"Elnozahy, E.N.M., Alvisi, L., Wang, Y.M., Johnson, D.B.: A survey of rollback-recovery protocols in message-passing systems. ACM Survey\u00a034, 375\u2013408 (2002)","journal-title":"ACM Survey"},{"key":"43_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1007\/978-3-642-23397-5_6","volume-title":"Euro-Par 2011 Parallel Processing","author":"A. Bouteiller","year":"2011","unstructured":"Bouteiller, A., Herault, T., Bosilca, G., Dongarra, J.J.: Correlated set coordination in fault tolerant message logging protocols. In: Jeannot, E., Namyst, R., Roman, J. (eds.) Euro-Par 2011, Part II. LNCS, vol.\u00a06853, pp. 51\u201364. Springer, Heidelberg (2011)"},{"key":"43_CR6","doi-asserted-by":"crossref","unstructured":"Guermouche, A., Ropars, T., Snir, M., Cappello, F.: HydEE: Failure containment without event logging for large scale send-deterministic MPI applications. In: Proc. 26th IPDPS, pp. 1216\u20131227. IEEE (May 2012)","DOI":"10.1109\/IPDPS.2012.111"},{"key":"43_CR7","doi-asserted-by":"crossref","unstructured":"Bosilca, G., Bouteiller, A., Brunet, E., Cappello, F., Dongarra, J., Guermouche, A., Herault, T., Robert, Y., Vivien, F., Zaidouni, D.: Unified model for assessing checkpointing protocols at extreme-scale. Research report RR-7950, INRIA (2012)","DOI":"10.1002\/cpe.3173"},{"issue":"6","key":"43_CR8","doi-asserted-by":"publisher","first-page":"518","DOI":"10.1109\/TC.1984.1676475","volume":"100","author":"K. Huang","year":"1984","unstructured":"Huang, K., Abraham, J.: Algorithm-based fault tolerance for matrix operations. IEEE Transactions on Computers\u00a0100(6), 518\u2013528 (1984)","journal-title":"IEEE Transactions on Computers"},{"key":"43_CR9","doi-asserted-by":"crossref","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: Proc. 10th ACM SIGPLAN PPoPP, pp. 213\u2013223. ACM (2005)","DOI":"10.1145\/1065944.1065973"},{"issue":"3","key":"43_CR10","first-page":"319","volume":"20","author":"A. Bouteiller","year":"2006","unstructured":"Bouteiller, A., Herault, T., Krawezik, G., Lemarinier, P., Cappello, F.: MPICH-V: a multiprotocol fault tolerant MPI. IJHPCA\u00a020(3), 319\u2013333 (2006)","journal-title":"IJHPCA"},{"key":"43_CR11","doi-asserted-by":"crossref","unstructured":"Bouteiller, A., Cappello, F., Dongarra, J., Guermouche, A., Herault, T., Robert, Y.: Multi-criteria checkpointing strategies: Optimizing response-time versus resource utilization. Research report ICL-UT-1301, University of Tennessee (February 2013)","DOI":"10.1007\/978-3-642-40047-6_43"},{"key":"43_CR12","doi-asserted-by":"crossref","unstructured":"Miyazaki, H., Kusano, Y., Okano, H., Nakada, T., Seki, K., Shimizu, T., Shinjo, N., Shoji, F., Uno, A., Kurokawa, M.: K computer: 8.162 petaflops massively parallel scalar supercomputer built with over 548k cores. In: ISSCC, pp. 192\u2013194. IEEE (2012)","DOI":"10.1109\/ISSCC.2012.6176971"},{"key":"43_CR13","doi-asserted-by":"crossref","unstructured":"Chakravorty, S., Kale, L.: A fault tolerance protocol with fast fault recovery. In: Proc. 21st IPDPS, pp. 1\u201310. IEEE (March 2007)","DOI":"10.1109\/IPDPS.2007.370310"},{"issue":"10","key":"43_CR14","doi-asserted-by":"publisher","first-page":"1471","DOI":"10.1109\/TPDS.2008.231","volume":"20","author":"X. Yang","year":"2009","unstructured":"Yang, X., Du, Y., Wang, P., Fu, H., Jia, J.: FTPA: Supporting fault-tolerant parallel computing through parallel recomputing. IEEE Transactions on Parallel and Distributed Systems\u00a020(10), 1471\u20131486 (2009)","journal-title":"IEEE Transactions on Parallel and Distributed Systems"},{"key":"43_CR15","doi-asserted-by":"publisher","first-page":"532","DOI":"10.1145\/42411.42415","volume":"31","author":"J.L. Gustafson","year":"1988","unstructured":"Gustafson, J.L.: Reevaluating Amdahl\u2019s law. Communications of the ACM\u00a031, 532\u2013533 (1988)","journal-title":"Communications of the ACM"},{"key":"43_CR16","doi-asserted-by":"crossref","unstructured":"Thekkath, R., Eggers, S.J.: The effectiveness of multiple hardware contexts. In: Proc. of the 6th ASPLOS, pp. 328\u2013337. ACM (1994)","DOI":"10.1145\/381792.195583"},{"key":"43_CR17","doi-asserted-by":"crossref","unstructured":"Huang, C., Zheng, G., Kal\u00e9, L., Kumar, S.: Performance evaluation of Adaptive MPI. In: Proc. 11th ACM SIGPLAN PPoPP, pp. 12\u201321. ACM (2006)","DOI":"10.1145\/1122971.1122976"},{"issue":"1","key":"43_CR18","first-page":"77","volume":"20","author":"A. Bouteiller","year":"2006","unstructured":"Bouteiller, A., Bouziane, H.L., Herault, T., Lemarinier, P., Cappello, F.: Hybrid preemptive scheduling of message passing interface applications on grids. IJHPCA\u00a020(1), 77\u201390 (2006)","journal-title":"IJHPCA"},{"issue":"3","key":"43_CR19","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1016\/j.future.2004.11.016","volume":"22","author":"J.T. Daly","year":"2004","unstructured":"Daly, J.T.: A higher order estimate of the optimum checkpoint interval for restart dumps. FGCS\u00a022(3), 303\u2013312 (2004)","journal-title":"FGCS"}],"container-title":["Lecture Notes in Computer Science","Euro-Par 2013 Parallel Processing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-40047-6_43","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,4,19]],"date-time":"2020-04-19T21:06:20Z","timestamp":1587330380000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-40047-6_43"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013]]},"ISBN":["9783642400469","9783642400476"],"references-count":19,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-40047-6_43","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2013]]},"assertion":[{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}
