{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T16:30:06Z","timestamp":1742920206605,"version":"3.40.3"},"publisher-location":"Cham","reference-count":14,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319038582"},{"type":"electronic","value":"9783319038599"}],"license":[{"start":{"date-parts":[[2013,1,1]],"date-time":"2013-01-01T00:00:00Z","timestamp":1356998400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2013,1,1]],"date-time":"2013-01-01T00:00:00Z","timestamp":1356998400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2013]]},"DOI":"10.1007\/978-3-319-03859-9_27","type":"book-chapter","created":{"date-parts":[[2013,12,9]],"date-time":"2013-12-09T12:54:34Z","timestamp":1386593674000},"page":"312-323","source":"Crossref","is-referenced-by-count":3,"title":["A Message Logging Protocol Based on User Level Failure Mitigation"],"prefix":"10.1007","author":[{"given":"Xunyun","family":"Liu","sequence":"first","affiliation":[]},{"given":"Xinhai","family":"Xu","sequence":"additional","affiliation":[]},{"given":"Xiaoguang","family":"Ren","sequence":"additional","affiliation":[]},{"given":"Yuhua","family":"Tang","sequence":"additional","affiliation":[]},{"given":"Ziqing","family":"Dai","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"27_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"499","DOI":"10.1007\/978-3-642-36949-0_57","volume-title":"Euro-Par 2012: Parallel Processing Workshops","author":"W. Bland","year":"2013","unstructured":"Bland, W.: User level failure mitigation in mpi. In: Caragiannis, I., Alexander, M., Badia, R.M., Cannataro, M., Costan, A., Danelutto, M., Desprez, F., Krammer, B., Sahuquillo, J., Scott, S.L., Weidendorfer, J. (eds.) Euro-Par Workshops 2012. LNCS, vol.\u00a07640, pp. 499\u2013504. Springer, Heidelberg (2013)"},{"key":"27_CR2","doi-asserted-by":"crossref","unstructured":"Meneses, E., Bronevetsky, G., Kale, L.V.: Evaluation of simple causal message logging for large-scale fault tolerant hpc systems. In: Proceedings of the 2011 IEEE International Symposium on Parallel and Distributed Processing Workshops and PhD Forum, IPDPSW 2011, pp. 1533\u20131540. IEEE Computer Society (2011)","DOI":"10.1109\/IPDPS.2011.307"},{"key":"27_CR3","doi-asserted-by":"publisher","first-page":"767","DOI":"10.1109\/TC.2011.106","volume":"61","author":"X. Yang","year":"2012","unstructured":"Yang, X., Wang, Z., Xue, J., Zhou, Y.: The reliability wall for exascale supercomputing. IEEE Transactions on Computers\u00a061, 767\u2013779 (2012)","journal-title":"IEEE Transactions on Computers"},{"key":"27_CR4","doi-asserted-by":"crossref","unstructured":"Xu, X., Yang, X., Lin, Y.: Wbc-alc: A weak blocking coordinated application-level checkpointing for mpi programs. IEICE Transactions, 786\u2013796 (2012)","DOI":"10.1587\/transinf.E95.D.786"},{"key":"27_CR5","doi-asserted-by":"crossref","unstructured":"Chakravorty, S., Kale, L.: A fault tolerance protocol with fast fault recovery. In: IEEE International Parallel and Distributed Processing Symposium, IPDPS 2007, pp. 1\u201310 (2007)","DOI":"10.1109\/IPDPS.2007.370310"},{"key":"27_CR6","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, 149\u2013159 (1998)","journal-title":"IEEE Trans. Softw. Eng."},{"key":"27_CR7","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":"27_CR8","doi-asserted-by":"publisher","first-page":"2196","DOI":"10.1002\/cpe.1589","volume":"22","author":"A. Bouteiller","year":"2010","unstructured":"Bouteiller, A., Bosilca, G., Dongarra, J.: Redesigning the message logging model for high performance. Concurr. Comput.: Pract. Exper.\u00a022, 2196\u20132211 (2010)","journal-title":"Concurr. Comput. : Pract. Exper."},{"key":"27_CR9","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: 2011 IEEE International Parallel Distributed Processing Symposium (IPDPS), pp. 989\u20131000 (2011)","DOI":"10.1109\/IPDPS.2011.95"},{"key":"27_CR10","doi-asserted-by":"crossref","unstructured":"Bouteiller, A., Ropars, T., Bosilca, G., Morin, C., Dongarra, J.: Reasons for a pessimistic or optimistic message logging protocol in mpi uncoordinated failure recovery. In: IEEE International Conference on Cluster Computing (Cluster 2009), New Orleans, \u00c9tats-Unis, pp. 1\u20139 (2009)","DOI":"10.1109\/CLUSTR.2009.5289157"},{"key":"27_CR11","unstructured":"Rabenseifner, R.: Automatic mpi counter profiling of all users: First results on a cray t3e 900-512. In: Proceedings of the Message Passing Interface Developer\u2019s and User\u2019s Conference(MPIDC 1999), pp. 77\u201385 (1999)"},{"key":"27_CR12","doi-asserted-by":"crossref","unstructured":"Patarasuk, P., Yuan, X.: Bandwidth efficient allreduce operation on tree topologies. In: IEEE IPDPS Workshop on High-Level Parallel Programming Models and Supportive Environments, pp. 1\u20138 (2007)","DOI":"10.1109\/IPDPS.2007.370405"},{"key":"27_CR13","doi-asserted-by":"publisher","first-page":"204","DOI":"10.1145\/3959.3962","volume":"3","author":"R. Strom","year":"1985","unstructured":"Strom, R., Yemini, S.: Optimistic recovery in distributed systems. ACM Trans. Comput. Syst.\u00a03, 204\u2013226 (1985)","journal-title":"ACM Trans. Comput. Syst."},{"key":"27_CR14","unstructured":"Zwaenepoel, W., Johnson, D.: Sender-Based Message Logging. In: Proceedings of the Seventeenth International Symposium on Fault-Tolerant Computing, pp. 49\u201366 (1987)"}],"container-title":["Lecture Notes in Computer Science","Algorithms and Architectures for Parallel Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-03859-9_27","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,7]],"date-time":"2023-02-07T19:26:24Z","timestamp":1675797984000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-319-03859-9_27"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013]]},"ISBN":["9783319038582","9783319038599"],"references-count":14,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-03859-9_27","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2013]]}}}