{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T10:04:58Z","timestamp":1743069898814,"version":"3.40.3"},"publisher-location":"Cham","reference-count":16,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319201184"},{"type":"electronic","value":"9783319201191"}],"license":[{"start":{"date-parts":[[2015,1,1]],"date-time":"2015-01-01T00:00:00Z","timestamp":1420070400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2015,1,1]],"date-time":"2015-01-01T00:00:00Z","timestamp":1420070400000},"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":[[2015]]},"DOI":"10.1007\/978-3-319-20119-1_15","type":"book-chapter","created":{"date-parts":[[2015,6,19]],"date-time":"2015-06-19T10:36:48Z","timestamp":1434710208000},"page":"197-211","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["An Efficient Clique-Based Algorithm of Compute Nodes Allocation for In-memory Checkpoint System"],"prefix":"10.1007","author":[{"given":"Xiangke","family":"Liao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Canqun","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhe","family":"Quan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tao","family":"Tang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cheng","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2015,6,20]]},"reference":[{"key":"15_CR1","unstructured":"http:\/\/source-forge.net\/projects\/scalablecr\/scalable-checkpoint\/restart-library"},{"key":"15_CR2","unstructured":"http:\/\/www.netlib.org\/utk\/people\/jackdongarra\/papers\/tianhe-2-dongarra-report.pdf"},{"issue":"3","key":"15_CR3","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. Future Gener. Comput. Syst. 22(3), 303\u2013312 (2006)","journal-title":"Future Gener. Comput. Syst."},{"issue":"5","key":"15_CR4","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1016\/0020-0190(83)90093-5","volume":"16","author":"A Duda","year":"1983","unstructured":"Duda, A.: The effects of checkpointing on program execution time. Inf. Process. Lett. 16(5), 221\u2013229 (1983)","journal-title":"Inf. Process. Lett."},{"key":"15_CR5","unstructured":"Vivek Sarkar, E.: Exascale software study: Software challenges in exascale systems (2009)"},{"key":"15_CR6","doi-asserted-by":"crossref","unstructured":"Glosli, J.N., Caspersen, K.J., Gunnels, J.A., Rudd, D.F.R.A.E., Streitz, F.H.: Extending stability beyond cpu millennium: a micron-scale atomistic simulation of kelvin-helmholtz instability. In: Proceedings of the 2007 ACM\/IEEE Conference on Supercomputing (SC), pp. 1\u201311 (2007)","DOI":"10.1145\/1362622.1362700"},{"key":"15_CR7","doi-asserted-by":"crossref","unstructured":"Iskra, K., Romein, J.W., Yoshii, K., Beckman, P.: Zoid: I\/o-forwarding infrastructure for petascale architectures. In: PPoPP 2008: Proceedings of the 13th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, pp. 153\u2013162 (2008)","DOI":"10.1145\/1345206.1345230"},{"issue":"3","key":"15_CR8","doi-asserted-by":"publisher","first-page":"329","DOI":"10.1109\/TDMR.2005.855685","volume":"5","author":"SE Michalak","year":"2005","unstructured":"Michalak, S.E., Harris, K.W., Hengartner, N.W., Takala, B.E., Wender, S.A.: Predicting the number of fatal soft errors in los alamos national laboratory\u2019s ASC Q supercomputer. IEEE Trans. Device Mater. Reliab. 5(3), 329\u2013335 (2005)","journal-title":"IEEE Trans. Device Mater. Reliab."},{"key":"15_CR9","unstructured":"Moody, A.: The scalable checkpoint\/restart (scr) library, user manual version 1.1-6 (2010)"},{"key":"15_CR10","doi-asserted-by":"crossref","unstructured":"Moody, A., Bronevetsky, G., Mohror, K., de Supinski, B.R.: Design, modeling, and evaluation of a scalable multi-level checkpointing system. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis(SC), pp. 13\u201329, November 2010","DOI":"10.2172\/984082"},{"key":"15_CR11","doi-asserted-by":"crossref","unstructured":"Naksinehaboon, N., Liu, Y., Leangsuksun, C.B., Nassar, R., Paun, M., Scott, S.L.: Reliability-aware approach: an incremental checkpoint\/restart model in hpc environments. In: Proceedings of the 2008 Eighth IEEE International Symposium on Cluster Computing and the Grid (CCGRID), pp. 783\u2013788 (2008)","DOI":"10.1109\/CCGRID.2008.109"},{"issue":"11","key":"15_CR12","doi-asserted-by":"publisher","first-page":"1570","DOI":"10.1006\/jpdc.2001.1757","volume":"61","author":"JS Plank","year":"2001","unstructured":"Plank, J.S., Thomason, M.G.: Processor allocation and checkpoint interval selection in cluster computing systems. J. Parallel Distrib. Comput. 61(11), 1570\u20131590 (2001)","journal-title":"J. Parallel Distrib. Comput."},{"key":"15_CR13","unstructured":"Ross, R., Moreira, J., Cupps, K., Pfeiffer, W.: Parallel i\/o on the ibm blue gene\/l system. Blue Gene\/L Consortium Quarterly Newsletter. Technical report (2006)"},{"key":"15_CR14","doi-asserted-by":"publisher","first-page":"012","DOI":"10.1088\/1742-6596\/78\/1\/012022","volume":"78","author":"B Schroeder","year":"2007","unstructured":"Schroeder, B., Gibson, G.: Understanding failure in petascale computers. J. Phys. Conf. Series: SciDAC 78, 012\u2013022 (2007)","journal-title":"J. Phys. Conf. Series: SciDAC"},{"key":"15_CR15","unstructured":"Schroeder, B., Gibson, G.A.: A large-scale study of failures in high-performance computing systems. In: Proceedings of the International Conference on Dependable Systems and Networks (DSN), pp. 249\u2013258 (2006)"},{"issue":"9","key":"15_CR16","doi-asserted-by":"publisher","first-page":"530","DOI":"10.1145\/361147.361115","volume":"17","author":"JW Young","year":"1974","unstructured":"Young, J.W.: A first order approximation to the optimum checkpoint interval. Commun. ACM 17(9), 530\u2013531 (1974)","journal-title":"Commun. ACM"}],"container-title":["Lecture Notes in Computer Science","High Performance Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-20119-1_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,21]],"date-time":"2023-02-21T01:40:10Z","timestamp":1676943610000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-319-20119-1_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015]]},"ISBN":["9783319201184","9783319201191"],"references-count":16,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-20119-1_15","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":"20 June 2015","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}