{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T11:43:00Z","timestamp":1743075780383,"version":"3.40.3"},"publisher-location":"Cham","reference-count":42,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319405261"},{"type":"electronic","value":"9783319405285"}],"license":[{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"content-version":"unspecified","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":[[2016]]},"DOI":"10.1007\/978-3-319-40528-5_18","type":"book-chapter","created":{"date-parts":[[2016,9,14]],"date-time":"2016-09-14T02:50:15Z","timestamp":1473821415000},"page":"405-426","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["FFMK: A Fast and Fault-Tolerant Microkernel-Based System for Exascale Computing"],"prefix":"10.1007","author":[{"given":"Carsten","family":"Weinhold","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Adam","family":"Lackorzynski","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jan","family":"Bierbaum","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Martin","family":"K\u00fcttler","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Maksym","family":"Planeta","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hermann","family":"H\u00e4rtig","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Amnon","family":"Shiloh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ely","family":"Levy","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tal","family":"Ben-Nun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Amnon","family":"Barak","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Thomas","family":"Steinke","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Thorsten","family":"Sch\u00fctt","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jan","family":"Fajerski","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alexander","family":"Reinefeld","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Matthias","family":"Lieber","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wolfgang E.","family":"Nagel","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2016,9,15]]},"reference":[{"key":"18_CR1","doi-asserted-by":"crossref","unstructured":"Acun, B., Gupta, A., Jain, N., Langer, A., Menon, H., Mikida, E., Ni, X., Robson, M., Sun, Y., Totoni, E., Wesolowski, L., Kale, L.: Parallel programming with migratable objects: Charm++ in practice. In: Proceedings of the Supercomputing 2014, Leipzig, pp. 647\u2013658. IEEE (2014)","DOI":"10.1109\/SC.2014.58"},{"key":"18_CR2","doi-asserted-by":"crossref","unstructured":"Arnold, D.C., Miller, B.P.: Scalable failure recovery for high-performance data aggregation. In: Proceedings of the IPDPS 2010, Atlanta, pp. 1\u201311. IEEE (2010)","DOI":"10.1109\/IPDPS.2010.5470432"},{"key":"18_CR3","doi-asserted-by":"crossref","unstructured":"Barak, A., Guday, S., Wheeler, R.: The MOSIX Distributed Operating System: Load Balancing for UNIX. Lecture Notes in Computer Science, vol. 672. Springer, Berlin\/New York (1993)","DOI":"10.1007\/3-540-56663-5"},{"key":"18_CR4","doi-asserted-by":"crossref","unstructured":"Barak, A., Margolin, A., Shiloh, A.: Automatic resource-centric process migration for MPI. In: Proceedings of the EuroMPI 2012. Lecture Notes in Computer Science, vol. 7490, pp. 163\u2013172. Springer, Berlin\/New York (2012)","DOI":"10.1007\/978-3-642-33518-1_21"},{"issue":"17","key":"18_CR5","doi-asserted-by":"publisher","first-page":"4797","DOI":"10.1002\/cpe.3465","volume":"27","author":"A. Barak","year":"2015","unstructured":"Barak, A., Drezner, Z., Levy, E., Lieber, M., Shiloh, A.: Resilient gossip algorithms for collecting online management information in exascale clusters. Concurr. Comput. Pract. Exper. 27 (17), 4797\u20134818 (2015)","journal-title":"Concurr. Comput. Pract. Exper."},{"key":"18_CR6","unstructured":"Beckman, P., et al.: Argo: an exascale operating system. \n                    http:\/\/www.argo-osr.org\/\n                    \n                  . Accessed 20 Nov 2015"},{"key":"18_CR7","doi-asserted-by":"crossref","unstructured":"Ben-Nun, T., Levy, E., Barak, A., Rubin, E.: Memory access patterns: the missing piece of the multi-GPU puzzle. In: Proceedings of the Supercomputing 2015, Newport Beach, pp. 19:1\u201319:12. ACM (2015)","DOI":"10.1145\/2807591.2807611"},{"key":"18_CR8","unstructured":"Berkeley Lab Checkpoint\/Restart. \n                    http:\/\/ftg.lbl.gov\/checkpoint\n                    \n                  . Accessed 20 Nov 2015"},{"key":"18_CR9","doi-asserted-by":"crossref","unstructured":"Brightwell, R., Oldfield, R., Maccabe, A.B., Bernholdt, D.E.: Hobbes: composition and virtualization as the foundations of an extreme-scale OS\/R. In: Proceedings of the ROSS\u201913, pp. 2:1\u20132:8. ACM (2013)","DOI":"10.1145\/2491661.2481427"},{"issue":"10","key":"18_CR10","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1145\/966049.781513","volume":"38","author":"G. Bronevetsky","year":"2003","unstructured":"Bronevetsky, G., Marques, D., Pingali, K., Stodghill, P.: Automated application-level checkpointing of MPI programs. ACM Sigplan Not. 38 (10), 84\u201394 (2003)","journal-title":"ACM Sigplan Not."},{"key":"18_CR11","doi-asserted-by":"crossref","unstructured":"Burstedde, C., Ghattas, O., Gurnis, M., Isaac, T., Stadler, G., Warburton, T., Wilcox, L.: Extreme-scale AMR. In: Proceedings of the Supercomputing 2010, Tsukuba, pp. 1\u201312. ACM (2010)","DOI":"10.1109\/SC.2010.25"},{"issue":"1","key":"18_CR12","first-page":"5","volume":"1","author":"F. Cappello","year":"2014","unstructured":"Cappello, F., Geist, A., Gropp, W., Kale, S., Kramer, B., Snir, M.: Toward exascale resilience: 2014 update. Supercomput. Front. Innov. 1 (1), 5\u201328 (2014)","journal-title":"Supercomput. Front. Innov."},{"issue":"1","key":"18_CR13","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1109\/4434.749133","volume":"7","author":"A. Corradi","year":"1999","unstructured":"Corradi, A., Leonardi, L., Zambonelli, F.: Diffusive load-balancing policies for dynamic applications. IEEE Concurr. 7 (1), 22\u201331 (1999)","journal-title":"IEEE Concurr."},{"issue":"1","key":"18_CR14","first-page":"3","volume":"25","author":"J. Dongarra","year":"2011","unstructured":"Dongarra, J., et al.: The international exascale software project roadmap. Int. J. High Speed Comput. 25 (1), 3\u201360 (2011)","journal-title":"Int. J. High Speed Comput."},{"key":"18_CR15","unstructured":"EXAHD \u2013 An Exa-Scalable Two-Level Sparse Grid Approach for Higher-Dimensional Problems in Plasma Physics and Beyond. \n                    http:\/\/ipvs.informatik.uni-stuttgart.de\/SGS\/EXAHD\/index.php\n                    \n                  . Accessed 29 Nov 2015"},{"key":"18_CR16","unstructured":"FFMK Website. \n                    http:\/\/ffmk.tudos.org\n                    \n                  . Accessed 20 Nov 2015"},{"key":"18_CR17","doi-asserted-by":"crossref","unstructured":"Harlacher, D.F., Klimach, H., Roller, S., Siebert, C., Wolf, F.: Dynamic load balancing for unstructured meshes on space-filling curves. In: Proceedings of the IPDPSW 2012, pp. 1661\u20131669. IEEE (2012)","DOI":"10.1109\/IPDPSW.2012.207"},{"key":"18_CR18","doi-asserted-by":"publisher","first-page":"265","DOI":"10.1002\/9780470558027.ch13","volume-title":"Advanced Computational Infrastructures for Parallel and Distributed Adaptive Applications, chap. 13","author":"L.V. Kale","year":"2009","unstructured":"Kale, L.V., Zheng, G.: Charm++ and AMPI: adaptive runtime strategies via migratable objects. In: Parashar, M., Li, X. (eds.) Advanced Computational Infrastructures for Parallel and Distributed Adaptive Applications, chap. 13, pp. 265\u2013282. Wiley, Hoboken (2009)"},{"issue":"6","key":"18_CR19","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1109\/MCSE.2013.95","volume":"15","author":"P. Kogge","year":"2013","unstructured":"Kogge, P., Shalf, J.: Exascale computing trends: adjusting to the \u201cNew Normal\u201d for computer architecture. Comput. Sci. Eng. 15 (6), 16\u201326 (2013)","journal-title":"Comput. Sci. Eng."},{"key":"18_CR20","unstructured":"Lackorzynski, A., Warg, A., Peter, M.: Generic virtualization with virtual processors. In: Proceedings of the 12th Real-Time Linux Workshop, Nairobi (2010)"},{"key":"18_CR21","doi-asserted-by":"crossref","unstructured":"Lange, J., Pedretti, K., Hudson, T., Dinda, P., Cui, Z., Xia, L., Bridges, P., Gocke, A., Jaconette, S., Levenhagen, M., Brightwell, R.: Palacios and Kitten: new high performance operating systems for scalable virtualized and native supercomputing. In: Proceedings of the IPDPS 2010, Atlanta, pp. 1\u201312. IEEE (2010)","DOI":"10.1109\/IPDPS.2010.5470482"},{"key":"18_CR22","doi-asserted-by":"crossref","unstructured":"Levy, E., Barak, A., Shiloh, A., Lieber, M., Weinhold, C., H\u00e4rtig, H.: Overhead of a decentralized gossip algorithm on the performance of HPC applications. In: Proceedings of the ROSS\u201914, Munich, pp. 10:1\u201310:7. ACM (2014)","DOI":"10.1145\/2612262.2612271"},{"key":"18_CR23","doi-asserted-by":"crossref","unstructured":"Lieber, M., Gr\u00fctzun, V., Wolke, R., M\u00fcller, M.S., Nagel, W.E.: Highly scalable dynamic load balancing in the atmospheric modeling system COSMO-SPECS+FD4. In: Proceedings of the PARA 2010. Lecture Notes in Computer Science, vol. 7133, pp. 131\u2013141. Springer, Berlin\/New York (2012)","DOI":"10.1007\/978-3-642-28151-8_13"},{"key":"18_CR24","doi-asserted-by":"crossref","unstructured":"Liedtke, J.: On micro-kernel construction. In: Proceedings of the 15th ACM Symposium on Operating Systems Principles (SOSP\u201995), Copper Mountain Resort, pp. 237\u2013250. ACM (1995)","DOI":"10.1145\/224056.224075"},{"key":"18_CR25","unstructured":"Lucas, R., et al.: Top ten exascale research challenges. DOE ASCAC subcommittee report. \n                    http:\/\/science.energy.gov\/~\/media\/ascr\/ascac\/pdf\/meetings\/20140210\/Top10reportFEB14.pdf\n                    \n                   (2014). Accessed 20 Nov 2015"},{"key":"18_CR26","doi-asserted-by":"crossref","unstructured":"Milthorpe, J., Ganesh, V., Rendell, A.P., Grove, D.: X10 as a parallel language for scientific computation: practice and experience. In: Proceedings of the IPDPS 2011, Anchorage, pp. 1080\u20131088. IEEE (2011)","DOI":"10.1109\/IPDPS.2011.103"},{"key":"18_CR27","doi-asserted-by":"crossref","unstructured":"Moody, A., Bronevetsky, G., Mohror, K., de Supinski, B.: Detailed modeling, design, and evaluation of a scalable multi-level checkpointing system. Technical report LLNL-TR-440491, Lawrence Livermore National Laboratory (LLNL) (2010)","DOI":"10.2172\/984082"},{"key":"18_CR28","unstructured":"MPI: A message-passing interface standard, version 3.1. \n                    http:\/\/www.mpi-forum.org\/docs\n                    \n                   (2015). Accessed 20 Nov 2015"},{"key":"18_CR29","unstructured":"Mvapich: Mpi over infiniband. \n                    http:\/\/mvapich.cse.ohio-state.edu\/\n                    \n                  . Accessed 20 Nov 2015"},{"key":"18_CR30","unstructured":"Open Source Molecular Dynamics. \n                    http:\/\/www.cp2k.org\/\n                    \n                  . Accessed 20 Nov 2015"},{"key":"18_CR31","doi-asserted-by":"crossref","unstructured":"Ouyang, X., Marcarelli, S., Rajachandrasekar, R., Panda, D.K.: RDMA-based job migration framework for MPI over Infiniband. In: Proceedings of the IEEE CLUSTER 2010, Heraklion, pp. 116\u2013125. IEEE (2010)","DOI":"10.1109\/CLUSTER.2010.20"},{"key":"18_CR32","doi-asserted-by":"crossref","unstructured":"Rajachandrasekar, R., Moody, A., Mohror, K., Panda, D.K.: A 1 PB\/s file system to checkpoint three million MPI tasks. In: Proceedings of the HPDC\u201913, New York, pp. 143\u2013154. ACM (2013)","DOI":"10.1145\/2493123.2462908"},{"key":"18_CR33","doi-asserted-by":"crossref","unstructured":"Roitzsch, M., Wachtler, S., H\u00e4rtig, H.: Atlas: look-ahead scheduling using workload metrics. In: Proceedings of the RTAS 2013, Philadelphia, pp. 1\u201310. IEEE (2013)","DOI":"10.1109\/RTAS.2013.6531074"},{"key":"18_CR34","doi-asserted-by":"crossref","unstructured":"Sato, K., Maruyama, N., Mohror, K., Moody, A., Gamblin, T., de Supinski, B.R., Matsuoka, S.: Design and modeling of a non-blocking checkpointing system. In: Proceedings of the Supercomputing 2012, Venice, pp. 19:1\u201319:10. IEEE (2012)","DOI":"10.1109\/SC.2012.46"},{"key":"18_CR35","first-page":"368","volume":"3","author":"M. Sato","year":"2013","unstructured":"Sato, M., Fukazawa, G., Yoshinaga, K., Tsujita, Y., Hori, A., Namiki, M.: A hybrid operating system for a computing node with multi-core and many-core processors. Int. J. Adv. Comput. Sci. 3, 368\u2013377 (2013)","journal-title":"Int. J. Adv. Comput. Sci."},{"issue":"2","key":"18_CR36","doi-asserted-by":"publisher","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. Par. Distrib. Comput. 72 (2), 254\u2013267 (2012)","journal-title":"J. Par. Distrib. Comput."},{"key":"18_CR37","unstructured":"Wende, F., Steinke, T., Reinefeld, A.: The impact of process placement and oversubscription on application performance: a case study for exascale computing. Technical report 15\u201305, ZIB (2015)"},{"issue":"4","key":"18_CR38","doi-asserted-by":"publisher","first-page":"880","DOI":"10.1016\/j.cpc.2011.12.013","volume":"183","author":"M. Winkel","year":"2012","unstructured":"Winkel, M., Speck, R., H\u00fcbner, H., Arnold, L., Krause, R., Gibbon, P.: A massively parallel, multi-disciplinary Barnes-Hut tree code for extreme-scale N-body simulations. Comput. Phys. Commun. 183 (4), 880\u2013889 (2012)","journal-title":"Comput. Phys. Commun."},{"key":"18_CR39","doi-asserted-by":"crossref","unstructured":"Wisniewski, R.W., Inglett, T., Keppel, P., Murty, R., Riesen, R.: mOS: an architecture for extreme-scale operating systems. In: Proceedings of the ROSS\u201914, Munich, pp. 2:1\u20132:8. ACM (2014)","DOI":"10.1145\/2612262.2612263"},{"key":"18_CR40","unstructured":"XtreemFS \u2013 a cloud file system. \n                    http:\/\/www.xtreemfs.org\n                    \n                  . Accessed 20 Nov 2015"},{"key":"18_CR41","doi-asserted-by":"crossref","unstructured":"Xue, M., Droegemeier, K.K., Weber, D.: Numerical prediction of high-impact local weather: a driver for petascale computing. In: Bader, D.A. (ed.) Petascale Computing: Algorithms and Applications, pp. 103\u2013124. Chapman & Hall\/CRC, Boca Raton (2008)","DOI":"10.1201\/9781584889106.ch6"},{"key":"18_CR42","doi-asserted-by":"crossref","unstructured":"Zheng, F., Yu, H., Hantas, C., Wolf, M., Eisenhauer, G., Schwan, K., Abbasi, H., Klasky, S.: Goldrush: resource efficient in situ scientific data analytics using fine-grained interference aware execution. In: Proceedings of the Supercomputing 2013, Eugene, pp. 78:1\u201378:12. ACM (2013)","DOI":"10.1145\/2503210.2503279"}],"container-title":["Lecture Notes in Computational Science and Engineering","Software for Exascale Computing - SPPEXA 2013-2015"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-40528-5_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,18]],"date-time":"2019-05-18T13:07:11Z","timestamp":1558184831000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-40528-5_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016]]},"ISBN":["9783319405261","9783319405285"],"references-count":42,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-40528-5_18","relation":{},"ISSN":["1439-7358","2197-7100"],"issn-type":[{"type":"print","value":"1439-7358"},{"type":"electronic","value":"2197-7100"}],"subject":[],"published":{"date-parts":[[2016]]},"assertion":[{"value":"15 September 2016","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}