{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,4]],"date-time":"2026-10-04T18:47:39Z","timestamp":1791139659702,"version":"4.1.0"},"publisher-location":"Berlin, Heidelberg","reference-count":19,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"value":"9783642233968","type":"print"},{"value":"9783642233975","type":"electronic"}],"license":[{"start":{"date-parts":[[2011,1,1]],"date-time":"2011-01-01T00:00:00Z","timestamp":1293840000000},"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":[[2011]]},"DOI":"10.1007\/978-3-642-23397-5_6","type":"book-chapter","created":{"date-parts":[[2011,8,18]],"date-time":"2011-08-18T07:40:06Z","timestamp":1313653206000},"page":"51-64","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":19,"title":["Correlated Set Coordination in Fault Tolerant Message Logging Protocols"],"prefix":"10.1007","author":[{"given":"Aurelien","family":"Bouteiller","sequence":"first","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 J.","family":"Dongarra","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","reference":[{"key":"6_CR1","volume-title":"29th Symposium on Fault-Tolerant Computing (FTCS 1999)","author":"L. Alvisi","year":"1999","unstructured":"Alvisi, L., Elnozahy, E., Rao, S., Husain, S.A., Mel, A.D.: An analysis of communication induced checkpointing. In: 29th Symposium on Fault-Tolerant Computing (FTCS 1999). IEEE CS Press, Los Alamitos (1999)"},{"key":"6_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"189","DOI":"10.1007\/978-3-642-15646-5_20","volume-title":"Recent Advances in the Message Passing Interface","author":"G. Bosilca","year":"2010","unstructured":"Bosilca, G., Bouteiller, A., Herault, T., Lemarinier, P., Dongarra, J.J.: Dodging the cost of unavoidable memory copies in message logging protocols. In: Keller, R., Gabriel, E., Resch, M., Dongarra, J. (eds.) EuroMPI 2010. LNCS, vol.\u00a06305, pp. 189\u2013197. Springer, Heidelberg (2010)"},{"key":"6_CR3","volume-title":"Proceedings of the International Supercomputer Conference (ISC 2008)","author":"A. Bouteiller","year":"2008","unstructured":"Bouteiller, A., Bosilca, G., Dongarra, J.: Redesigning the message logging model for high performance. In: ISC 2008, Wiley, Dresden (June 2008) (p. to appear)"},{"key":"6_CR4","unstructured":"Bouteiller, A., Ropars, T., Bosilca, G., Morin, C., Dongarra, J.: Reasons to be pessimist or optimist for failure recovery in high performance clusters. In: IEEE (ed.) Proceedings of the 2009 IEEE Cluster Conference (September 2009)"},{"issue":"1","key":"6_CR5","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1016\/j.future.2007.02.002","volume":"24","author":"D. Buntinas","year":"2008","unstructured":"Buntinas, D., Coti, C., Herault, T., Lemarinier, P., Pilard, L., Rezmerita, A., Rodriguez, E., Cappello, F.: Blocking vs. non-blocking coordinated checkpointing for large-scale fault tolerant MPI protocols. Future Generation Computer Systems\u00a024(1), 73\u201384 (2008), http:\/\/www.sciencedirect.com\/science\/article\/B6V06-4N2KT6H-1\/2\/00e790651475028977cc3031d9ea3980","journal-title":"Future Generation Computer Systems"},{"issue":"1","key":"6_CR6","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. Transactions on Computer Systems\u00a03(1), 63\u201375 (1985)","journal-title":"Transactions on Computer Systems"},{"key":"6_CR7","unstructured":"Dongarra, J., Beckman, P., et al.: The international exascale software roadmap. Intl. Journal of High Performance Computer Applications\u00a025(11) (to appear) (2011)"},{"key":"6_CR8","doi-asserted-by":"crossref","unstructured":"Esteban Meneses, C.L.M., Kal\u00e9, L.V.: Team-based message logging: Preliminary results. In: 3rd Workshop on Resiliency in High Performance Computing (Resilience) in Clusters, Clouds, and Grids (CCGRID 2010) (May 2010)","DOI":"10.1109\/CCGRID.2010.110"},{"key":"6_CR9","doi-asserted-by":"crossref","unstructured":"Gabriel, E., Fagg, G.E., Bosilca, G., Angskun, T., Dongarra, J.J., Squyres, J.M., Sahay, V., Kambadur, P., Barrett, B., Lumsdaine, A., Castain, R.H., Daniel, D.J., Graham, R.L., Woodall, T.S.: Open MPI: Goals, concept, and design of a next generation MPI implementation. In: Proceedings, 11th European PVM\/MPI Users\u2019 Group Meeting, Budapest, Hungary, pp. 97\u2013104 (September 2004)","DOI":"10.1007\/978-3-540-30218-6_19"},{"key":"6_CR10","doi-asserted-by":"crossref","unstructured":"Gao, Q., Huang, W., Koop, M.J., Panda, D.K.: Group-based coordinated checkpointing for mpi: A case study on infiniband. In: International Conference on Parallel Processing, ICPP 2007 (2007)","DOI":"10.1109\/ICPP.2007.44"},{"key":"6_CR11","first-page":"1","volume-title":"Proceedings of the 22nd IEEE International Symposium on Parallel and Distributed Processing (IPDPS)","author":"J.C.Y. Ho","year":"2008","unstructured":"Ho, J.C.Y., Wang, C.L., Lau, F.C.M.: Scalable Group-based Checkpoint\/Restart for Large-Scale Message-Passing Systems. In: Proceedings of the 22nd IEEE International Symposium on Parallel and Distributed Processing (IPDPS), pp. 1\u201312. IEEE, Los Alamitos (2008)"},{"issue":"9","key":"6_CR12","doi-asserted-by":"publisher","first-page":"865","DOI":"10.1109\/71.798312","volume":"10","author":"J.M. Hlary","year":"1999","unstructured":"Hlary, J.M., Mostefaoui, A., Raynal, M.: Communication-induced determination of consistent snapshots. IEEE Transactions on Parallel and Distributed Systems\u00a010(9), 865\u2013877 (1999)","journal-title":"IEEE Transactions on Parallel and Distributed Systems"},{"key":"6_CR13","volume-title":"Encyclopedia of Parallel Computing","author":"L. Kale","year":"2011","unstructured":"Kale, L.: Charm++. In: Padua, D. (ed.) Encyclopedia of Parallel Computing, Springer, Heidelberg (to appear) (2011)"},{"issue":"7","key":"6_CR14","doi-asserted-by":"publisher","first-page":"558","DOI":"10.1145\/359545.359563","volume":"21","author":"L. Lamport","year":"1978","unstructured":"Lamport, L.: Time, clocks, and the ordering of events in a distributed system. Communications of the ACM\u00a021(7), 558\u2013565 (1978)","journal-title":"Communications of the ACM"},{"key":"6_CR15","volume-title":"IEEE International Conference on Cluster Computing","author":"P. Lemarinier","year":"2004","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. IEEE CS Press, Los Alamitos (2004)"},{"key":"6_CR16","unstructured":"Negara, S., Pan, K.C., Zheng, G., Negara, N., Johnson, R.E., Kale, L.V., Ricker, P.M.: Automatic MPI to AMPI Program Transformation. Tech. Rep. 10-09, Parallel Programming Laboratory (March 2010)"},{"key":"6_CR17","unstructured":"Plank, J.S.: Efficient Checkpointing on MIMD Architectures. Ph.D. thesis, Princeton University (June 1993), http:\/\/www.cs.utk.edu\/~plank\/plank\/papers\/thesis.html"},{"key":"6_CR18","first-page":"10","volume-title":"17th Symposium on Reliable Distributed Systems (SRDS)","author":"S. Rao","year":"1998","unstructured":"Rao, S., Alvisi, L., Vin, H.M.: The cost of recovery in message logging protocols. In: 17th Symposium on Reliable Distributed Systems (SRDS), October 1998, pp. 10\u201318. IEEE CS Press, Los Alamitos (1998)"},{"key":"6_CR19","doi-asserted-by":"crossref","unstructured":"The MPI Forum: MPI: a message passing interface. In: Supercomputing 1993: Proceedings of the 1993 ACM\/IEEE Conference on Supercomputing, pp. 878\u2013883. ACM Press, New York (1993)","DOI":"10.1145\/169627.169855"}],"container-title":["Lecture Notes in Computer Science","Euro-Par 2011 Parallel Processing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-23397-5_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,8]],"date-time":"2025-03-08T22:17:57Z","timestamp":1741472277000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-23397-5_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2011]]},"ISBN":["9783642233968","9783642233975"],"references-count":19,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-23397-5_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2011]]},"assertion":[{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}