{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,4]],"date-time":"2025-05-04T01:50:18Z","timestamp":1746323418161,"version":"3.40.3"},"publisher-location":"Berlin, Heidelberg","reference-count":30,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642246685"},{"type":"electronic","value":"9783642246692"}],"license":[{"start":{"date-parts":[[2011,1,1]],"date-time":"2011-01-01T00:00:00Z","timestamp":1293840000000},"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":[[2011]]},"DOI":"10.1007\/978-3-642-24669-2_11","type":"book-chapter","created":{"date-parts":[[2011,10,22]],"date-time":"2011-10-22T10:05:36Z","timestamp":1319277936000},"page":"109-120","source":"Crossref","is-referenced-by-count":18,"title":["SpotMPI: A Framework for Auction-Based HPC Computing Using Amazon Spot Instances"],"prefix":"10.1007","author":[{"given":"Moussa","family":"Taifi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Justin Y.","family":"Shi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Abdallah","family":"Khreishah","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"11_CR1","unstructured":"Starcluster (2010), http:\/\/web.mit.edu\/stardev\/cluster\/"},{"key":"11_CR2","unstructured":"Amazon hpc cluster instances (2011), http:\/\/aws.amazon.com\/ec2\/hpc-applications\/"},{"key":"11_CR3","doi-asserted-by":"crossref","unstructured":"Agbaria, A.M., Friedman, R.: Starfish: fault-tolerant dynamic mpi programs on clusters of workstations. In: Proceedings of the Eighth International Symposium on High Performance Distributed Computing, 1999, pp. 167\u2013176 (1999)","DOI":"10.1109\/HPDC.1999.805295"},{"key":"11_CR4","first-page":"483","volume-title":"Proceedings of the Spring Joint Computer Conference","author":"G.M. Amdahl","year":"1967","unstructured":"Amdahl, G.M.: Validity of the single processor approach to achieving large scale computing capabilities. In: Proceedings of the Spring Joint Computer Conference, April 18-20, pp. 483\u2013485. ACM, New York (1967)"},{"key":"11_CR5","doi-asserted-by":"crossref","unstructured":"Andrzejak, A., Kondo, D., Yi, S.: Decision model for cloud computing under sla constraints. In: Proc. IEEE Int Modeling, Analysis & Simulation of Computer and Telecommunication Systems (MASCOTS) Symp., pp. 257\u2013266 (2010)","DOI":"10.1109\/MASCOTS.2010.34"},{"key":"11_CR6","doi-asserted-by":"publisher","first-page":"164","DOI":"10.1145\/945445.945462","volume-title":"Proceedings of the Nineteenth ACM Symposium on Operating Systems Principles","author":"P. Barham","year":"2003","unstructured":"Barham, P., Dragovic, B., Fraser, K., Hand, S., Harris, T., Ho, A., Neugebauer, R., Pratt, I., Warfield, A.: Xen and the art of virtualization. In: Proceedings of the Nineteenth ACM Symposium on Operating Systems Principles, pp. 164\u2013177. ACM, New York (2003)"},{"issue":"3","key":"11_CR7","doi-asserted-by":"publisher","first-page":"446","DOI":"10.1006\/jpdc.1999.1549","volume":"58","author":"K. Blathras","year":"1999","unstructured":"Blathras, K., Szyld, D.B., Shi, Y.: Timing models and local stopping criteria for asynchronous iterative algorithms. Journal of Parallel and Distributed Computing\u00a058(3), 446\u2013465 (1999)","journal-title":"Journal of Parallel and Distributed Computing"},{"key":"11_CR8","unstructured":"Borthakur, D.: The hadoop distributed file system: Architecture and design (2007), http:\/\/developer.yahoo.com\/hadoop\/tutorial\/"},{"key":"11_CR9","unstructured":"Chohan, N., Castillo, C., Spreitzer, M., Steinder, M., Tantawi, A., Krintz, C.: See spot run: using spot instances for mapreduce workflows. In: Proceedings of the 2nd USENIX Conference on Hot Topics in Cloud Computing, p. 7. USENIX Association (2010)"},{"issue":"3","key":"11_CR10","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1016\/j.future.2004.11.016","volume":"22","author":"J.T. Daly","year":"2006","unstructured":"Daly, J.T.: A higher order estimate of the optimum checkpoint interval for restart dumps. Future Generation Computer Systems\u00a022(3), 303\u2013312 (2006)","journal-title":"Future Generation Computer Systems"},{"issue":"1","key":"11_CR11","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1145\/1327452.1327492","volume":"51","author":"J. Dean","year":"2008","unstructured":"Dean, J., Ghemawat, S.: Mapreduce: Simplified data processing on large clusters. Communications of the ACM\u00a051(1), 107\u2013113 (2008)","journal-title":"Communications of the ACM"},{"key":"11_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"346","DOI":"10.1007\/3-540-45255-9_47","volume-title":"Recent Advances in Parallel Virtual Machine and Message Passing Interface","author":"G. Fagg","year":"2000","unstructured":"Fagg, G., Dongarra, J.: Ft-mpi: Fault tolerant mpi, supporting dynamic applications in a dynamic world. In: Dongarra, J., Kacsuk, P., Podhorszki, N. (eds.) PVM\/MPI 2000. LNCS, vol.\u00a01908, pp. 346\u2013353. Springer, Heidelberg (2000)"},{"issue":"4","key":"11_CR13","doi-asserted-by":"publisher","first-page":"285","DOI":"10.1023\/A:1024504726988","volume":"31","author":"R.L. Graham","year":"2003","unstructured":"Graham, R.L., Choi, S.E., Daniel, D.J., Desai, N.N., Minnich, R.G., Rasmussen, C.E., Risinger, L.D., Sukalski, M.W.: A network-failure-tolerant message-passing system for terascale clusters. International Journal of Parallel Programming\u00a031(4), 285\u2013303 (2003)","journal-title":"International Journal of Parallel Programming"},{"key":"11_CR14","doi-asserted-by":"crossref","unstructured":"Hargrove, P.H., Duell, J.C.: Berkeley lab checkpoint\/restart (blcr) for linux clusters. In: Journal of Physics: Conference Series, vol.\u00a046, p. 494. IOP Publishing (2006)","DOI":"10.1088\/1742-6596\/46\/1\/067"},{"key":"11_CR15","unstructured":"Hursey, J.: Coordinated Checkpoint\/Restart Process Fault Tolerance for MPI Applications on HPC Systems. PhD thesis, Indiana University, Bloomington, IN, USA (July 2010)"},{"key":"11_CR16","doi-asserted-by":"crossref","unstructured":"Hursey, J., Squyres, J.M., Mattox, T.I., Lumsdaine, A.: The design and implementation of checkpoint\/restart process fault tolerance for open mpi. In: Proc. IEEE Int. Parallel and Distributed Processing Symp. IPDPS 2007, pp. 1\u20138 (2007)","DOI":"10.1109\/IPDPS.2007.370605"},{"issue":"6","key":"11_CR17","doi-asserted-by":"publisher","first-page":"931","DOI":"10.1109\/TPDS.2011.66","volume":"22","author":"A. Iosup","year":"2011","unstructured":"Iosup, A., Ostermann, S., Yigitbasi, N., Prodan, R., Fahringer, T., Epema, D.: Performance analysis of cloud computing services for many-tasks scientific computing. IEEE Transactions on Parallel and Distributed Systems\u00a022(6), 931\u2013945 (2011)","journal-title":"IEEE Transactions on Parallel and Distributed Systems"},{"key":"11_CR18","unstructured":"Litzkow, M., Tannenbaum, T., Basney, J., Livny, M.: Checkpoint and migration of unix processes in the condor distributed processing system. Technical report, Technical Report (1997)"},{"key":"11_CR19","unstructured":"Lusk, E.: Fault tolerance in mpi programs. Special issue of the Journal High Performance Computing Applications, IJHPCA (2002)"},{"key":"11_CR20","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: Proc. Int. High Performance Computing, Networking, Storage and Analysis (SC) Conf. for, pp. 1\u201311 (2010)","DOI":"10.2172\/984082"},{"key":"11_CR21","first-page":"48","volume-title":"Twenty-Ninth Annual International Symposium on Fault-Tolerant Computing, 1999. Digest of Papers","author":"S. Rao","year":"1999","unstructured":"Rao, S., Alvisi, L., Vin, H.M.: Egida: An extensible toolkit for low-overhead fault-tolerance. In: Twenty-Ninth Annual International Symposium on Fault-Tolerant Computing, 1999. Digest of Papers, pp. 48\u201355. IEEE, Los Alamitos (1999)"},{"key":"11_CR22","volume-title":"International Conference on Distributed and Parallel Processing","author":"J.Y. Shi","year":"1997","unstructured":"Shi, J.Y.: Program scalability analysis. In: International Conference on Distributed and Parallel Processing. Geogetown University, Washington D.C (1997)"},{"key":"11_CR23","doi-asserted-by":"crossref","unstructured":"Shi, J.Y., Taifi, M., Khreishah, A., Wu, J.: Sustainable gpu computing at scale. In: 14th IEEE International Conference in Computational Science and Engneering 2011 (2011)","DOI":"10.1109\/CSE.2011.55"},{"key":"11_CR24","first-page":"526","volume-title":"Proceedings of the 10th International Parallel Processing Symposium, IPPS 1996","author":"G. Stellner","year":"1996","unstructured":"Stellner, G.: Cocheck: Checkpointing and process migration for mpi. In: Proceedings of the 10th International Parallel Processing Symposium, IPPS 1996, pp. 526\u2013531. IEEE Computer Society, Washington, DC, USA (1996)"},{"key":"11_CR25","doi-asserted-by":"crossref","unstructured":"Vecchiola, C., Pandey, S., Buyya, R.: High-performance cloud computing: A view of scientific applications. In: Proc. 10th Int. Pervasive Systems, Algorithms, and Networks (ISPAN) Symp., pp. 4\u201316 (2009)","DOI":"10.1109\/I-SPAN.2009.150"},{"key":"11_CR26","doi-asserted-by":"publisher","first-page":"236","DOI":"10.1109\/CLOUD.2010.35","volume-title":"2010 IEEE 3rd International Conference on Cloud Computing","author":"S. Yi","year":"2010","unstructured":"Yi, S., Kondo, D., Andrzejak, A.: Reducing costs of spot instances via checkpointing in the amazon elastic compute cloud. In: 2010 IEEE 3rd International Conference on Cloud Computing, pp. 236\u2013243. IEEE, Los Alamitos (2010)"},{"issue":"9","key":"11_CR27","doi-asserted-by":"publisher","first-page":"530","DOI":"10.1145\/361147.361115","volume":"17","author":"J.W. Young","year":"1974","unstructured":"Young, J.W.: A first order approximation to the optimum checkpoint interval. Communications of the ACM\u00a017(9), 530\u2013531 (1974)","journal-title":"Communications of the ACM"},{"key":"11_CR28","first-page":"1","volume-title":"Proceedings of the 2nd International Workshop on Virtualization Technology in Distributed computing","author":"L. Youseff","year":"2006","unstructured":"Youseff, L., Wolski, R., Gorda, B., Krintz, C.: Evaluating the performance impact of xen on mpi and process execution for hpc systems. In: Proceedings of the 2nd International Workshop on Virtualization Technology in Distributed computing, p. 1. IEEE Computer Society, Los Alamitos (2006)"},{"key":"11_CR29","unstructured":"Zhang, Q., Grses, E., Boutaba, R., Xiao, J.: Dynamic resource allocation for spot markets in clouds. In: Proceedings of the 11th USENIX Conference on Hot Topics in Management of Internet, Cloud, and Enterprise Networks and Services (2011)"},{"key":"11_CR30","first-page":"93","volume-title":"2004 IEEE International Conference on Cluster Computing","author":"G. Zheng","year":"2004","unstructured":"Zheng, G., Shi, L., Kal\u00e9, L.V.: Ftc-charm++: An in-memory checkpoint-based fault tolerant runtime for charm++ and mpi. In: 2004 IEEE International Conference on Cluster Computing, pp. 93\u2013103. IEEE, Los Alamitos (2004)"}],"container-title":["Lecture Notes in Computer Science","Algorithms and Architectures for Parallel Processing"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-24669-2_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,6,18]],"date-time":"2019-06-18T08:04:22Z","timestamp":1560845062000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-24669-2_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2011]]},"ISBN":["9783642246685","9783642246692"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-24669-2_11","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2011]]}}}