{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,22]],"date-time":"2025-06-22T12:10:06Z","timestamp":1750594206783,"version":"3.41.0"},"publisher-location":"Cham","reference-count":22,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319619811"},{"type":"electronic","value":"9783319619828"}],"license":[{"start":{"date-parts":[[2017,1,1]],"date-time":"2017-01-01T00:00:00Z","timestamp":1483228800000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017]]},"DOI":"10.1007\/978-3-319-61982-8_18","type":"book-chapter","created":{"date-parts":[[2017,7,13]],"date-time":"2017-07-13T09:22:20Z","timestamp":1499937740000},"page":"191-205","source":"Crossref","is-referenced-by-count":4,"title":["An Application-Level Solution for the Dynamic Reconfiguration of MPI Applications"],"prefix":"10.1007","author":[{"given":"Iv\u00e1n","family":"Cores","sequence":"first","affiliation":[]},{"given":"Patricia","family":"Gonz\u00e1lez","sequence":"additional","affiliation":[]},{"given":"Emmanuel","family":"Jeannot","sequence":"additional","affiliation":[]},{"given":"Mar\u00eda J.","family":"Mart\u00edn","sequence":"additional","affiliation":[]},{"given":"Gabriel","family":"Rodr\u00edguez","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2017,7,14]]},"reference":[{"issue":"3","key":"18_CR1","doi-asserted-by":"crossref","first-page":"227","DOI":"10.1023\/A:1023540604208","volume":"6","author":"A Agbaria","year":"2003","unstructured":"Agbaria, A., Friedman, R.: Starfish: fault-tolerant dynamic MPI programs on clusters of workstations. Cluster Comput. 6(3), 227\u2013236 (2003)","journal-title":"Cluster Comput."},{"key":"18_CR2","doi-asserted-by":"crossref","unstructured":"Broquedis, F., Clet-Ortega, J., Moreaud, S., Furmento, N., Goglin, B., Mercier, G., Thibault, S., Namyst, R.: hwloc: a generic framework for managing hardware affinities in HPC applications. In: Euromicro International Conference on Parallel, Distributed and Network-Based Processing (PDP), pp. 180\u2013186 (2010)","DOI":"10.1109\/PDP.2010.67"},{"key":"18_CR3","doi-asserted-by":"crossref","unstructured":"Buisson, J., Sonmez, O., Mohamed, H., Lammers, W., Epema, D.: Scheduling malleable applications in multicluster systems. In: 2007 International Conference on Cluster Computing (CLUSTER), pp. 372\u2013381 (2007)","DOI":"10.1109\/CLUSTR.2007.4629252"},{"key":"18_CR4","doi-asserted-by":"crossref","unstructured":"Cores, I., Rodr\u00edguez, G., Mart\u00edn, M.J., Gonz\u00e1lez, P.: Achieving checkpointing global consistency through a hybrid compile time and runtime protocol. Procedia Comput. Sci. 18, 169\u2013178 (2013). International Conference on Computational Science (ICCS)","DOI":"10.1016\/j.procs.2013.05.180"},{"key":"18_CR5","doi-asserted-by":"crossref","first-page":"166","DOI":"10.1016\/j.procs.2012.04.018","volume":"9","author":"C George","year":"2012","unstructured":"George, C., Vadhiyar, S.S.: ADFT: an adaptive framework for fault tolerance on large scale systems using application malleability. Procedia Comput. Sci. 9, 166\u2013175 (2012). International Conference on Computational Science (ICCS)","journal-title":"Procedia Comput. Sci."},{"key":"18_CR6","doi-asserted-by":"crossref","first-page":"39","DOI":"10.1016\/j.jpdc.2015.01.004","volume":"78","author":"WL Guay","year":"2015","unstructured":"Guay, W.L., Reinemo, S.A., Johnsen, B.D., Yen, C.H., Skeie, T., Lysne, O., T\u00f8rudbakken, O.: Early experiences with live migration of SR-IOV enabled infiniband. J. Parallel Distrib. Comput. 78, 39\u201352 (2015)","journal-title":"J. Parallel Distrib. Comput."},{"issue":"1","key":"18_CR7","doi-asserted-by":"crossref","first-page":"45","DOI":"10.1504\/IJSSC.2012.045562","volume":"2","author":"TJ Hacker","year":"2012","unstructured":"Hacker, T.J., Romero, F., Nielsen, J.J.: Secure live migration of parallel applications using container-based virtual machines. Int. J. Space Based Situated Comput. 2(1), 45\u201357 (2012)","journal-title":"Int. J. Space Based Situated Comput."},{"key":"18_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"306","DOI":"10.1007\/978-3-540-24644-2_20","volume-title":"Languages and Compilers for Parallel Computing","author":"C Huang","year":"2004","unstructured":"Huang, C., Lawlor, O., Kal\u00e9, L.V.: Adaptive MPI. In: Rauchwerger, L. (ed.) LCPC 2003. LNCS, vol. 2958, pp. 306\u2013322. Springer, Heidelberg (2004). doi: 10.1007\/978-3-540-24644-2_20"},{"key":"18_CR9","doi-asserted-by":"crossref","unstructured":"Hungershofer, J.: On the combined scheduling of malleable and rigid jobs. In: Computer Architecture and High Performance Computing (SBAC-PAD), pp. 206\u2013213 (2004)","DOI":"10.1109\/SBAC-PAD.2004.27"},{"key":"18_CR10","unstructured":"Information Technology Center, RIKEN. HIMENO Benchmark. http:\/\/accc.riken.jp\/2444.htm . Accessed Aug 2016"},{"key":"18_CR11","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"199","DOI":"10.1007\/978-3-642-15291-7_20","volume-title":"Euro-Par 2010 - Parallel Processing","author":"E Jeannot","year":"2010","unstructured":"Jeannot, E., Mercier, G.: Near-optimal placement of MPI processes on hierarchical NUMA architectures. In: D\u2019Ambra, P., Guarracino, M., Talia, D. (eds.) Euro-Par 2010. LNCS, vol. 6272, pp. 199\u2013210. Springer, Heidelberg (2010). doi: 10.1007\/978-3-642-15291-7_20"},{"key":"18_CR12","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1016\/j.parco.2015.04.003","volume":"46","author":"G Mart\u00edn","year":"2015","unstructured":"Mart\u00edn, G., Singh, D.E., Marinescu, M.C., Carretero, J.: Enhancing the performance of malleable MPI applications by using performance-aware dynamic reconfiguration. Parallel Comput. 46, 60\u201377 (2015)","journal-title":"Parallel Comput."},{"key":"18_CR13","doi-asserted-by":"crossref","unstructured":"Nagarajan, A.B., Mueller, F., Engelmann, C., Scott, S.L.: Proactive fault tolerance for HPC with Xen virtualization. In: International Conference on Supercomputing (ICS), pp. 23\u201332 (2007)","DOI":"10.1145\/1274971.1274978"},{"key":"18_CR14","unstructured":"National Aeronautics and Space Administration. The NAS Parallel Benchmarks. http:\/\/www.nas.nasa.gov\/publications\/npb.html . Accessed Aug 2016"},{"key":"18_CR15","unstructured":"Open MPI Team. Open MPI: Open Source High Performance Computing. http:\/\/www.open-mpi.org\/ . Accessed Aug 2016"},{"key":"18_CR16","doi-asserted-by":"crossref","unstructured":"Raveendran, A., Bicer, T., Agrawal, G.: A framework for elastic execution of existing MPI programs. In: IEEE International Symposium on Parallel and Distributed Processing Workshops (IPDPSW), pp. 940\u2013947 (2011)","DOI":"10.1109\/IPDPS.2011.240"},{"key":"18_CR17","doi-asserted-by":"crossref","unstructured":"Ribeiro, F.S., Nascimento, A.P., Boeres, C., Rebello, V.E.F., Sena, A.C.: Autonomic malleability in iterative MPI applications. In: Computer Architecture and High Performance Computing (SBAC-PAD), pp. 192\u2013199 (2013)","DOI":"10.1109\/SBAC-PAD.2013.4"},{"issue":"6","key":"18_CR18","doi-asserted-by":"crossref","first-page":"749","DOI":"10.1002\/cpe.1541","volume":"22","author":"G Rodr\u00edguez","year":"2010","unstructured":"Rodr\u00edguez, G., Mart\u00edn, M.J., Gonz\u00e1lez, P., Touri\u00f1o, J., Doallo, R.: CPPC: a compiler-assisted tool for portable checkpointing of message-passing applications. Concurr. Comput. Pract. Exper. 22(6), 749\u2013766 (2010)","journal-title":"Concurr. Comput. Pract. Exper."},{"key":"18_CR19","doi-asserted-by":"crossref","unstructured":"Rodr\u00edguez, M., Cores, I., Gonz\u00e1lez, P., Mart\u00edn, M.J.: Improving an MPI application-level migration approach through checkpoint file splitting. In: Computer Architecture and High Performance Computing (SBAC-PAD), pp. 33\u201340 (2014)","DOI":"10.1109\/SBAC-PAD.2014.25"},{"issue":"02","key":"18_CR20","doi-asserted-by":"crossref","first-page":"291","DOI":"10.1142\/S0129626403001288","volume":"13","author":"SS Vadhiyar","year":"2003","unstructured":"Vadhiyar, S.S., Dongarra, J.J.: SRS - a framework for developing malleable and migratable parallel applications for distributed systems. Parallel Process. Lett. 13(02), 291\u2013312 (2003)","journal-title":"Parallel Process. Lett."},{"issue":"2","key":"18_CR21","doi-asserted-by":"crossref","first-page":"254","DOI":"10.1016\/j.jpdc.2011.10.009","volume":"72","author":"C Wang","year":"2012","unstructured":"Wang, C., Mueller, F., Engelmann, C., Scott, S.L.: Proactive process-level live migration and back migration in HPC environments. J. Parallel Distrib. Comput. 72(2), 254\u2013267 (2012)","journal-title":"J. Parallel Distrib. Comput."},{"key":"18_CR22","doi-asserted-by":"crossref","unstructured":"Weatherly, D.B., Lowenthal, D.K., Nakazawa, M., Lowenthal, F.: Dyn-MPI: supporting MPI on non dedicated clusters. In: ACM\/IEEE Conference on High Performance Networking and Computing (SC), p. 5 (2003)","DOI":"10.1145\/1048935.1050156"}],"container-title":["Lecture Notes in Computer Science","High Performance Computing for Computational Science \u2013 VECPAR 2016"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-61982-8_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,22]],"date-time":"2025-06-22T11:35:02Z","timestamp":1750592102000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-61982-8_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017]]},"ISBN":["9783319619811","9783319619828"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-61982-8_18","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2017]]}}}