{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T04:13:16Z","timestamp":1748751196590,"version":"3.41.0"},"publisher-location":"Cham","reference-count":18,"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_52","type":"book-chapter","created":{"date-parts":[[2015,12,17]],"date-time":"2015-12-17T13:29:53Z","timestamp":1450358993000},"page":"644-655","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Addressing the Last Roadblock for Message Logging in HPC: Alleviating the Memory Requirement Using Dedicated Resources"],"prefix":"10.1007","author":[{"given":"Tatiana","family":"Martsinkevich","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Thomas","family":"Ropars","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Franck","family":"Cappello","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2015,12,18]]},"reference":[{"issue":"2","key":"52_CR1","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. 24(2), 149\u2013159 (1998)","journal-title":"IEEE Trans. Softw. Eng."},{"key":"52_CR2","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. Concurrency Comput. Pract. Experience 22, 2196\u20132211 (2010)","journal-title":"Concurrency Comput. Pract. Experience"},{"key":"52_CR3","doi-asserted-by":"crossref","unstructured":"Bouteiller, A., Collin, B., Herault, T., Lemarinier, P., Cappello, F.: Impact of event logger on causal message logging protocols for fault tolerant MPI. In: Proceedings of the 19th IEEE International Parallel and Distributed Processing Symposium (IPDPS 2005), vol. 1, p. 97, April 2005","DOI":"10.1109\/IPDPS.2005.249"},{"key":"52_CR4","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. 6853, pp. 51\u201364. Springer, Heidelberg (2011)"},{"issue":"1","key":"52_CR5","first-page":"1","volume":"1","author":"F Cappello","year":"2014","unstructured":"Cappello, F., Geist, A., Gropp, B., Kale, L., Kramer, B., Snir, M.: Toward exascale resilience: 2014 update. Supercomput. Front. Innovations 1(1), 1\u201328 (2014)","journal-title":"Supercomput. Front. Innovations"},{"key":"52_CR6","doi-asserted-by":"crossref","unstructured":"Cappello, F., Guermouche, A., Snir, M.: On communication determinism in parallel HPC applications. In: 19th International Conference on Computer Communications and Networks (ICCCN 2010) (2010)","DOI":"10.1109\/ICCCN.2010.5560143"},{"key":"52_CR7","doi-asserted-by":"crossref","unstructured":"Cores, I., Rodriguez, G., Martin, M., Gonz\u00e1lez, P.: Reducing application-level checkpoint file sizes: towards scalable fault tolerance solutions. In: 2012 IEEE 10th International Symposium on Parallel and Distributed Processing with Applications, pp. 371\u2013378, July 2012","DOI":"10.1109\/ISPA.2012.55"},{"key":"52_CR8","doi-asserted-by":"crossref","unstructured":"Di Martino, C., Kalbarczyk, Z., Iyer, R., Baccanico, F., Fullop, J., Kramer, W.: Lessons learned from the analysis of system failures at petascale: the case of Blue Waters. In: 2014 44th Annual IEEE\/IFIP International Conference on Dependable Systems and Networks (DSN), pp. 610\u2013621, June 2014","DOI":"10.1109\/DSN.2014.62"},{"key":"52_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1007\/978-3-642-36949-0_54","volume-title":"Euro-Par 2012: Parallel Processing Workshops","author":"KB Ferreira","year":"2013","unstructured":"Ferreira, K.B., Riesen, R., Arnold, D., Ibtesham, D., Brightwell, R.: The viability of using compression to decrease message log sizes. 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. 7640, pp. 484\u2013493. Springer, Heidelberg (2013)"},{"key":"52_CR10","doi-asserted-by":"crossref","unstructured":"Jin, H., Ke, T., Chen, Y., Sun, X.H.: Checkpointing orchestration: toward a scalable hpc fault-tolerant environment. In: Proceedings of the 2012 12th IEEE\/ACM International Symposium on Cluster, Cloud and Grid Computing, CCGRID 2012, pp. 276\u2013283 (2012)","DOI":"10.1109\/CCGrid.2012.61"},{"key":"52_CR11","unstructured":"Johnson, D.B., Zwaenepoel, W.: Sender-based message logging. In: Digest of Papers: The 17th Annual International Symposium on Fault-Tolerant Computing, pp. 14\u201319 (1987)"},{"key":"52_CR12","doi-asserted-by":"crossref","unstructured":"Meneses, E., Mendes, C.L., Kal\u00e9, L.V.: Team-based message logging: preliminary results. In: Proceedings of the 2010 10th IEEE\/ACM International Conference on Cluster, Cloud and Grid Computing, CCGRID 2010, pp. 697\u2013702 (2010)","DOI":"10.1109\/CCGRID.2010.110"},{"key":"52_CR13","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 2010 ACM\/IEEE International Conference for High Performance Computing, Networking, Storage and Analysis, SC 2010, pp. 1\u201311 (2010)","DOI":"10.1109\/SC.2010.18"},{"key":"52_CR14","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: IEEE\/ACM SuperComputing 2012, SC 2012 (2012)","DOI":"10.1109\/SC.2012.18"},{"key":"52_CR15","doi-asserted-by":"crossref","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: Proceedings of the 17th international conference on Parallel processing, Euro-Par 2011, pp. 567\u2013578 (2011)","DOI":"10.1007\/978-3-642-23400-2_53"},{"key":"52_CR16","doi-asserted-by":"crossref","unstructured":"Ropars, T., Martsinkevich, T., Guermouche, A., Schiper, A., Cappello, F.: SPBC: Leveraging the characteristics of MPI HPC applications for scalable checkpointing. In: IEEE\/ACM SuperComputing 2013 (SC13) (2013)","DOI":"10.1145\/2503210.2503271"},{"issue":"17","key":"52_CR17","doi-asserted-by":"publisher","first-page":"2167","DOI":"10.1002\/cpe.1775","volume":"23","author":"T Ropars","year":"2011","unstructured":"Ropars, T., Morin, C.: Active optimistic and distributed message logging for message-passing applications. Concurrency Comput. Pract. Experience 23(17), 2167\u20132178 (2011)","journal-title":"Concurrency Comput. Pract. Experience"},{"issue":"9","key":"52_CR18","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","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_52","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,31]],"date-time":"2025-05-31T20:48:32Z","timestamp":1748724512000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-27308-2_52"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015]]},"ISBN":["9783319273075","9783319273082"],"references-count":18,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-27308-2_52","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"}]}}