{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,8]],"date-time":"2024-09-08T10:34:52Z","timestamp":1725791692906},"publisher-location":"Berlin, Heidelberg","reference-count":28,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642544194"},{"type":"electronic","value":"9783642544200"}],"license":[{"start":{"date-parts":[[2014,1,1]],"date-time":"2014-01-01T00:00:00Z","timestamp":1388534400000},"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":[[2014]]},"DOI":"10.1007\/978-3-642-54420-0_70","type":"book-chapter","created":{"date-parts":[[2014,4,9]],"date-time":"2014-04-09T21:40:41Z","timestamp":1397079641000},"page":"717-726","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Asking the Right Questions: Benchmarking Fault-Tolerant Extreme-Scale Systems"],"prefix":"10.1007","author":[{"given":"Patrick M.","family":"Widener","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kurt B.","family":"Ferreira","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Scott","family":"Levy","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Patrick G.","family":"Bridges","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dorian","family":"Arnold","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ron","family":"Brightwell","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"issue":"1","key":"70_CR1","doi-asserted-by":"publisher","first-page":"63","DOI":"10.1145\/214451.214456","volume":"3","author":"K.M. Chandy","year":"1985","unstructured":"Chandy, K.M., Lamport, L.: Distributed snapshots: determining global states of distributed systems. ACM Trans. Comput. Syst.\u00a03(1), 63\u201375 (1985)","journal-title":"ACM Trans. Comput. Syst."},{"unstructured":"Ahn, J.: 2-step algorithm for enhancing effectiveness of sender-based message logging. In: SpringSim 2007: Proceedings of the 2007 Spring Simulation Multiconference, pp. 429\u2013434 (2007)","key":"70_CR2"},{"doi-asserted-by":"crossref","unstructured":"Jiang, Q., Manivannan, D.: An optimistic checkpointing and selective message logging approach for consistent global checkpoint collection in distributed systems. In: Proceedings of the 2007 IEEE International Parallel and Distributed Processing Symposium (March 2007)","key":"70_CR3","DOI":"10.1109\/IPDPS.2007.370308"},{"doi-asserted-by":"crossref","unstructured":"Johnson, D.B., Zwaenepoel, W.: Recovery in distributed systems using asynchronous message logging and checkpointing. In: Proceedings of the Seventh Annual ACM Symposium on Principles of Distributed Computing, pp. 171\u2013181 (1988)","key":"70_CR4","DOI":"10.1145\/62546.62575"},{"issue":"2","key":"70_CR5","doi-asserted-by":"publisher","first-page":"149","DOI":"10.1109\/32.666828","volume":"24","author":"L. Alvisi","year":"1998","unstructured":"Alvisi, L., Marzullo, K.: Message logging: Pessimistic, optimistic, causal, and optimal. IEEE Trans. Softw. Eng.\u00a024(2), 149\u2013159 (1998)","journal-title":"IEEE Trans. Softw. Eng."},{"issue":"3","key":"70_CR6","doi-asserted-by":"publisher","first-page":"375","DOI":"10.1145\/568522.568525","volume":"34","author":"E.N. (Mootaz) Elnozahy","year":"2002","unstructured":"(Mootaz) Elnozahy, E.N., Alvisi, L., Wang, Y.-M., Johnson, D.B.: A survey of rollback-recovery protocols in message-passing systems. ACM Comput. Surv.\u00a034(3), 375\u2013408 (2002)","journal-title":"ACM Comput. Surv."},{"doi-asserted-by":"crossref","unstructured":"Bosilca, G., Bouteiller, A., Cappello, F., Djilali, S., Fedak, G., Germain, C., Herault, T., Lemarinier, P., Lodygensky, O., Magniette, F., Neri, V., Selikhov, A.: MPICH-V: Toward a scalable fault tolerant mpi for volatile nodes. In: Conference on High Performance Networking and Computing (SC 2002), Baltimore, MD, pp. 1\u201318 (November 2002)","key":"70_CR7","DOI":"10.1109\/SC.2002.10048"},{"doi-asserted-by":"crossref","unstructured":"Lemarinier, P., Bouteiller, A., Herault, T., Krawezik, G., Cappello, F.: Improved message logging versus improved coordinated checkpointing for fault tolerant MPI. In: IEEE International Conference on Cluster Computing, pp. 115\u2013124 (2004)","key":"70_CR8","DOI":"10.1109\/CLUSTR.2003.1253321"},{"issue":"1","key":"70_CR9","doi-asserted-by":"publisher","first-page":"42","DOI":"10.1145\/1057977.1057980","volume":"37","author":"Y. Saito","year":"2005","unstructured":"Saito, Y., Shapiro, M.: Optimistic replication. ACM Comput. Surv.\u00a037(1), 42\u201381 (2005)","journal-title":"ACM Comput. Surv."},{"issue":"9","key":"70_CR10","doi-asserted-by":"publisher","first-page":"803","DOI":"10.1002\/cpe.728","volume":"15","author":"J.J. Dongarra","year":"2003","unstructured":"Dongarra, J.J., Luszczek, P., Petitet, A.: The linpack benchmark: past, present and future. Concurrency and Computation: practice and experience\u00a015(9), 803\u2013820 (2003)","journal-title":"Concurrency and Computation: practice and experience"},{"unstructured":"Van der Wijngaart, R.F., Wong, P.: NAS parallel benchmarks version 2.4. Technical report, NAS technical report, NAS-02-007 (2002)","key":"70_CR11"},{"unstructured":"Antypas, K., Shalf, J., Wasserman, H.: NERSC-6 workload analysis and benchmark selection process. Technical Report LBLNL-1014E, Lawrence Berkeley National Laboratories (2000)","key":"70_CR12"},{"unstructured":"Sandia National Laboratories. Mantevo, \n                    \n                      http:\/\/software.sandia.gov\/mantevo","key":"70_CR13"},{"unstructured":"CESAR, Argonne National Laboratory. The CESAR Proxy-apps, \n                    \n                      https:\/\/cesar.mcs.anl.gov\/content\/software\n                    \n                    \n                   (retrieved June 10, 2013)","key":"70_CR14"},{"doi-asserted-by":"crossref","unstructured":"Ferreira, K.B., Levy, S., Bridges, P.G.: A simulation infrastructure for examining the performance of resilience strategies at scale. Technical Report SAND 2013-3180, Sandia National Laboratories (April 2013)","key":"70_CR15","DOI":"10.2172\/1088091"},{"doi-asserted-by":"crossref","unstructured":"Hoefler, T., Schneider, T., Lumsdaine, A.: Loggopsim: simulating large-scale applications in the LogGOPS model. In: Proceedings of the 19th ACM International Symposium on High Performance Distributed Computing, pp. 597\u2013604. ACM (2010)","key":"70_CR16","DOI":"10.1145\/1851476.1851564"},{"doi-asserted-by":"crossref","unstructured":"Riesen, R., Ferreira, K., Da Silva, D., Lemarinier, P., Arnold, D., Bridges, P.G.: Alleviating scalability issues of checkpointing protocols. In: Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis, SC 2012, Los Alamitos, CA, USA, pp. 18:1\u201318:11. IEEE Computer Society Press (2012)","key":"70_CR17","DOI":"10.1109\/SC.2012.18"},{"doi-asserted-by":"crossref","unstructured":"Guermouche, A., Ropars, T., Snir, M., HydEE, F.C.: Failure containment without event logging for large scale send-deterministic MPI applications. In: IPDPS, pp. 1216\u20131227. IEEE Computer Society (2012)","key":"70_CR18","DOI":"10.1109\/IPDPS.2012.111"},{"key":"70_CR19","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"567","DOI":"10.1007\/978-3-642-23400-2_53","volume-title":"Euro-Par 2011 Parallel Processing","author":"T. Ropars","year":"2011","unstructured":"Ropars, T., Guermouche, A., U\u00e7ar, B., Meneses, E., Kal\u00e9, L.V., Cappello, F.: On the Use of Cluster-Based Partial Message Logging to Improve Fault Tolerance for MPI HPC Applications. In: Jeannot, E., Namyst, R., Roman, J. (eds.) Euro-Par 2011, Part I. LNCS, vol.\u00a06852, pp. 567\u2013578. Springer, Heidelberg (2011)"},{"doi-asserted-by":"crossref","unstructured":"Guermouche, A., Ropars, T., Brunet, E., Snir, M., Cappello, F.: Uncoordinated checkpointing without domino effect for send-deterministic MPI applications. In: International Parallel Distributed Processing Symposium (IPDPS), pp. 989\u20131000 (May 2011)","key":"70_CR20","DOI":"10.1109\/IPDPS.2011.95"},{"unstructured":"Sandia National Laboratory. Mantevo project home page, \n                    \n                      https:\/\/software.sandia.gov\/mantevo\n                    \n                    \n                   (April 10, 2010)","key":"70_CR21"},{"unstructured":"Lawrence Livermore\u00a0National Laboratory. Asc sequoia benchmark codes, \n                    \n                      https:\/\/asc.llnl.gov\/sequoia\/benchmarks\/#amg\n                    \n                    \n                   (April 6, 2013)","key":"70_CR22"},{"key":"70_CR23","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1006\/jcph.1995.1039","volume":"117","author":"S.J. Plimpton","year":"1995","unstructured":"Plimpton, S.J.: Fast parallel algorithms for short-range molecular dynamics. Journal Computation Physics\u00a0117, 1\u201319 (1995)","journal-title":"Journal Computation Physics"},{"unstructured":"Sandia National Laboratory. LAMMPS molecular dynamics simulator, \n                    \n                      http:\/\/lammps.sandia.gov\n                    \n                    \n                   (April 10, 2010)","key":"70_CR24"},{"unstructured":"Advanced Scientific Computing Research program, Office of Science, US Department of Energy. SciDAC Co-Design, \n                    \n                      http:\/\/science.energy.gov\/ascr\/research\/scidac\/co-design\/\n                    \n                    \n                   (retrieved June 10, 2013)","key":"70_CR25"},{"unstructured":"Center for Exascale Simulation of Combustion in Turbulence (ExaCT), \n                    \n                      http:\/\/exactcodesign.org\/\n                    \n                    \n                   (retrieved June 10, 2013)","key":"70_CR26"},{"unstructured":"Exascale Co-Design Center for Materials in Extreme Environments (ExMatEx), \n                    \n                      http:\/\/exmatex.lanl.gov\/\n                    \n                    \n                   (retrieved June 10, 2013)","key":"70_CR27"},{"unstructured":"Center for Exascale Simulation of Advanced Reactors (CESAR), \n                    \n                      https:\/\/cesar.mcs.anl.gov\/\n                    \n                    \n                   (retrieved June 10, 2013)","key":"70_CR28"}],"container-title":["Lecture Notes in Computer Science","Euro-Par 2013: Parallel Processing Workshops"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-54420-0_70","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,4,20]],"date-time":"2020-04-20T00:13:42Z","timestamp":1587341622000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-54420-0_70"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014]]},"ISBN":["9783642544194","9783642544200"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-54420-0_70","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2014]]},"assertion":[{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}