{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,16]],"date-time":"2025-11-16T01:55:13Z","timestamp":1763258113856},"publisher-location":"Cham","reference-count":17,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319273075"},{"type":"electronic","value":"9783319273082"}],"license":[{"start":{"date-parts":[[2015,1,1]],"date-time":"2015-01-01T00:00:00Z","timestamp":1420070400000},"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":[[2015]]},"DOI":"10.1007\/978-3-319-27308-2_53","type":"book-chapter","created":{"date-parts":[[2015,12,17]],"date-time":"2015-12-17T13:29:53Z","timestamp":1450358993000},"page":"656-668","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Towards Understanding Post-recovery Efficiency for Shrinking and Non-shrinking Recovery"],"prefix":"10.1007","author":[{"given":"Aiman","family":"Fang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hajime","family":"Fujita","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andrew A.","family":"Chien","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2015,12,18]]},"reference":[{"key":"53_CR1","unstructured":"Mira. \n                      https:\/\/www.alcf.anl.gov\/mira"},{"key":"53_CR2","unstructured":"Running jobs. \n                      https:\/\/www.alcf.anl.gov\/user-guides\/running-jobs"},{"key":"53_CR3","doi-asserted-by":"crossref","unstructured":"Bhandarkar, M.A., et al.: Adaptive load balancing for mpi programs. In: International Conference on Computational Science, ICCS 2001 (2001)","DOI":"10.1007\/3-540-45718-6_13"},{"key":"53_CR4","doi-asserted-by":"crossref","unstructured":"Bhatele, A., et al.: Mapping applications with collectives over sub-communicators on torus networks. In: Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis, SC 2012 (2012)","DOI":"10.1109\/SC.2012.75"},{"key":"53_CR5","doi-asserted-by":"crossref","unstructured":"Bhatele, A., et al.: Optimizing the performance of parallel applications on a 5d torus via task mapping. In: IEEE International Conference on High Performance Computing. IEEE Computer Society (2014)","DOI":"10.1109\/HiPC.2014.7116706"},{"key":"53_CR6","doi-asserted-by":"crossref","unstructured":"Bland, W., et al.: An evaluation of user-level failure mitigation support in MPI. In: Proceedings of the 19th European Conference on Recent Advances in the Message Passing Interface, EuroMPI 2012 (2012)","DOI":"10.1007\/978-3-642-33518-1_24"},{"issue":"3","key":"53_CR7","doi-asserted-by":"publisher","first-page":"212","DOI":"10.1177\/1094342009106189","volume":"23","author":"F Cappello","year":"2009","unstructured":"Cappello, F.: Fault tolerance in petascale\/exascale systems: current knowledge, challenges and research opportunities. Int. J. High Perform. Comput. Appl. 23(3), 212\u2013226 (2009)","journal-title":"Int. J. High Perform. Comput. Appl."},{"issue":"1","key":"53_CR8","first-page":"5","volume":"1","author":"F Cappello","year":"2014","unstructured":"Cappello, F., Geist, A., Gropp, W., Kale, S., Kramer, B., Snir, M.: Toward exascale resilience: 2014 update. Supercomput. Front. Innovations 1(1), 5\u201328 (2014)","journal-title":"Supercomput. Front. Innovations"},{"key":"53_CR9","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1016\/0743-7315(89)90021-X","volume":"7","author":"G Cybenko","year":"1989","unstructured":"Cybenko, G.: Dynamic load balancing for distributed memory multiprocessors. J. Parallel Distrib. Comput. 7, 279\u2013301 (1989)","journal-title":"J. Parallel Distrib. Comput."},{"key":"53_CR10","doi-asserted-by":"crossref","unstructured":"Heroux, M.A.: Toward resilient algorithms and applications. In: Proceedings of the 3rd Workshop on Fault-tolerance for HPC at extreme scale, FTXS 2013 (2013)","DOI":"10.1145\/2465813.2465814"},{"key":"53_CR11","doi-asserted-by":"crossref","unstructured":"Laguna, I., et al.: Evaluating user-level fault tolerance for MPI applications. In: Proceedings of the 21st European MPI Users\u2019 Group Meeting, EuroMPI\/ASIA 2014 (2014)","DOI":"10.1145\/2642769.2642775"},{"key":"53_CR12","doi-asserted-by":"crossref","unstructured":"Moody, A., Bronevetsky, G., Mohror, K., Supinski, B.R.d.: Design, modeling, and evaluation of a scalable multi-level checkpointing system. In: Proceedings of the 2010 ACM\/IEEE International Conference for High Performance Computing, Networking, Storage and Analysis, SC 2010 (2010)","DOI":"10.1109\/SC.2010.18"},{"key":"53_CR13","doi-asserted-by":"crossref","unstructured":"Pearce, O., et al.: Load balancing n-body simulations with highly non-uniform density. In: Proceedings of the 28th ACM International Conference on Supercomputing, ICS 2014 (2014)","DOI":"10.1145\/2597652.2597659"},{"key":"53_CR14","doi-asserted-by":"crossref","unstructured":"Schloegel, K., et al.: A unified algorithm for load-balancing adaptive scientific simulations. In: Proceedings of the 2000 ACM\/IEEE Conference on Supercomputing, SC 2000 (2000)","DOI":"10.1109\/SC.2000.10035"},{"issue":"2","key":"53_CR15","doi-asserted-by":"publisher","first-page":"129","DOI":"10.1177\/1094342014522573","volume":"28","author":"M Snir","year":"2013","unstructured":"Snir, M., et al.: Addressing failures in exascale computing*. Int. J. High Perform. Comput. IJHPC 28(2), 129\u2013173 (2013)","journal-title":"Int. J. High Perform. Comput. IJHPC"},{"key":"53_CR16","doi-asserted-by":"crossref","unstructured":"Teranishi, K., Heroux, M.A.: Toward local failure local recovery resilience model using MPI-ULFM. In: Proceedings of the 21st European MPI Users\u2019 Group Meeting, EuroMPI\/ASIA 2014 (2014)","DOI":"10.1145\/2642769.2642774"},{"key":"53_CR17","doi-asserted-by":"crossref","unstructured":"Widener, P., Ferreira, K.B., Levy, S., Hoefler, T.: Exploring the effect of noise on the performance benefit of nonblocking allreduce. In: Proceedings of the 21st European MPI Users\u2019 Group Meeting, EuroMPI\/ASIA 2014 (2014)","DOI":"10.1145\/2642769.2642786"}],"container-title":["Lecture Notes in Computer Science","Euro-Par 2015: Parallel Processing Workshops"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-27308-2_53","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,4,20]],"date-time":"2020-04-20T00:42:36Z","timestamp":1587343356000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-27308-2_53"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015]]},"ISBN":["9783319273075","9783319273082"],"references-count":17,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-27308-2_53","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2015]]},"assertion":[{"value":"18 December 2015","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}