{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T12:14:54Z","timestamp":1763468094868},"publisher-location":"Berlin, Heidelberg","reference-count":20,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642335174"},{"type":"electronic","value":"9783642335181"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2012]]},"DOI":"10.1007\/978-3-642-33518-1_24","type":"book-chapter","created":{"date-parts":[[2012,9,8]],"date-time":"2012-09-08T12:17:23Z","timestamp":1347106643000},"page":"193-203","source":"Crossref","is-referenced-by-count":60,"title":["An Evaluation of User-Level Failure Mitigation Support in MPI"],"prefix":"10.1007","author":[{"given":"Wesley","family":"Bland","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aurelien","family":"Bouteiller","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Thomas","family":"Herault","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Joshua","family":"Hursey","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"George","family":"Bosilca","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jack J.","family":"Dongarra","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"24_CR1","unstructured":"Bland, W., Bosilca, G., Bouteiller, A., Herault, T., Dongarra, J.: A proposal for User-Level Failure Mitigation in the MPI-3 standard. Tech. rep., Department of Electrical Engineering and Computer Science, University of Tennessee (2012)"},{"key":"24_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"crossref","first-page":"477","DOI":"10.1007\/978-3-642-32820-6_48","volume-title":"Euro-Par 2012","author":"W. Bland","year":"2012","unstructured":"Bland, W., Du, P., Bouteiller, A., Herault, T., Bosilca, G., Dongarra, J.: A Checkpoint-on-Failure Protocol for Algorithm-Based Recovery in Standard MPI. In: Kaklamanis, C., Papatheodorou, P., Spirakis, P.G. (eds.) Euro-Par 2012. LNCS, vol.\u00a07484, pp. 477\u2013488. Springer, Heidelberg (2012)"},{"key":"24_CR3","doi-asserted-by":"crossref","unstructured":"Bosilca, G., Bouteiller, A., Brunet, \u00c9., Cappello, F., Dongarra, J., Guermouche, A., H\u00e9rault, T., Robert, Y., Vivien, F., Zaidouni, D.: Unified Model for Assessing Checkpointing Protocols at Extreme-Scale. Tech. report RR-7950, INRIA (2012)","DOI":"10.1002\/cpe.3173"},{"key":"24_CR4","unstructured":"Bougeret, M., Casanova, H., Robert, Y., Vivien, F., Zaidouni, D.: Using group replication for resilience on exascale systems. Tech. Rep. 265, LAWNs (2012)"},{"issue":"16","key":"24_CR5","first-page":"2196","volume":"22","author":"A. Bouteiller","year":"2010","unstructured":"Bouteiller, A., Bosilca, G., Dongarra, J.: Redesigning the message logging model for high performance. CCPE\u00a022(16), 2196\u20132211 (2010)","journal-title":"CCPE"},{"issue":"1","key":"24_CR6","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1016\/j.future.2007.02.002","volume":"24","author":"D. Buntinas","year":"2008","unstructured":"Buntinas, D., Coti, C., Herault, T., Lemarinier, P., Pilard, L., Rezmerita, A., Rodriguez, E., Cappello, F.: Blocking vs. non-blocking coordinated checkpointing for large-scale fault tolerant MPI protocols. FGCS\u00a024(1), 73\u201384 (2008)","journal-title":"FGCS"},{"issue":"4","key":"24_CR7","first-page":"374","volume":"23","author":"F. Cappello","year":"2009","unstructured":"Cappello, F., Geist, A., Gropp, B., Kal\u00e9, L.V., Kramer, B., Snir, M.: Toward exascale resilience. IJHPCA\u00a023(4), 374\u2013388 (2009)","journal-title":"IJHPCA"},{"key":"24_CR8","doi-asserted-by":"crossref","unstructured":"Davies, T., Karlsson, C., Liu, H., Ding, C., Chen, Z.: High Performance Linpack Benchmark: A Fault Tolerant Implementation without Checkpointing. In: 25th ICS, pp. 162\u2013171. ACM (2011)","DOI":"10.1145\/1995896.1995923"},{"issue":"11","key":"24_CR9","first-page":"3","volume":"25","author":"J. Dongarra","year":"2011","unstructured":"Dongarra, J., Beckman, P., et al.: The international exascale software roadmap. IJHPCA\u00a025(11), 3\u201360 (2011)","journal-title":"IJHPCA"},{"key":"24_CR10","doi-asserted-by":"crossref","unstructured":"Du, P., Bouteiller, A., et al.: Algorithm-based fault tolerance for dense matrix factorizations. In: 17th SIGPLAN PPoPP, pp. 225\u2013234. ACM (2012)","DOI":"10.1145\/2145816.2145845"},{"key":"24_CR11","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.E. Fagg","year":"2000","unstructured":"Fagg, G.E., Dongarra, J.J.: FT-MPI: Fault Tolerant MPI, Supporting Dynamic Applications in a Dynamic World. In: Dongarra, J., Kacsuk, P., Podhorszki, N. (eds.) EuroPVM\/MPI 2000. LNCS, vol.\u00a01908, pp. 346\u2013353. Springer, Heidelberg (2000)"},{"key":"24_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"97","DOI":"10.1007\/978-3-540-30218-6_19","volume-title":"Recent Advances in Parallel Virtual Machine and Message Passing Interface","author":"E. Gabriel","year":"2004","unstructured":"Gabriel, E., Fagg, G.E., Bosilca, G., Angskun, T., Dongarra, J., Squyres, J.M., Sahay, V., Kambadur, P., Barrett, B.W., Lumsdaine, A., Castain, R.H., Daniel, D.J., Graham, R.L., Woodall, T.S.: Open MPI: Goals, Concept, and Design of a Next Generation MPI Implementation. In: Kranzlm\u00fcller, D., Kacsuk, P., Dongarra, J. (eds.) EuroPVM\/MPI 2004. LNCS, vol.\u00a03241, pp. 97\u2013104. Springer, Heidelberg (2004)"},{"key":"24_CR13","first-page":"363","volume":"18","author":"W. Gropp","year":"2004","unstructured":"Gropp, W., Lusk, E.: Fault tolerance in message passing interface programs. IJHPCA\u00a018, 363\u2013372 (2004)","journal-title":"IJHPCA"},{"key":"24_CR14","unstructured":"Hadzilacos, V., Toueg, S.: Fault-tolerant broadcasts and related problems. In: Distributed Systems, 2nd edn., pp. 97\u2013145. ACM\/Addison-Wesley (1993)"},{"issue":"6","key":"24_CR15","doi-asserted-by":"publisher","first-page":"518","DOI":"10.1109\/TC.1984.1676475","volume":"100","author":"K. Huang","year":"1984","unstructured":"Huang, K., Abraham, J.: Algorithm-based fault tolerance for matrix operations. IEEE Transactions on Computers\u00a0100(6), 518\u2013528 (1984)","journal-title":"IEEE Transactions on Computers"},{"key":"24_CR16","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"329","DOI":"10.1007\/978-3-642-24449-0_40","volume-title":"Recent Advances in the Message Passing Interface","author":"J. Hursey","year":"2011","unstructured":"Hursey, J., Graham, R.L., Bronevetsky, G., Buntinas, D., Pritchard, H., Solt, D.G.: Run-Through Stabilization: An MPI Proposal for Process Fault Tolerance. In: Cotronis, Y., Danalis, A., Nikolopoulos, D.S., Dongarra, J. (eds.) EuroMPI 2011. LNCS, vol.\u00a06960, pp. 329\u2013332. Springer, Heidelberg (2011)"},{"key":"24_CR17","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"255","DOI":"10.1007\/978-3-642-24449-0_29","volume-title":"Recent Advances in the Message Passing Interface","author":"J. Hursey","year":"2011","unstructured":"Hursey, J., Naughton, T., Vallee, G., Graham, R.L.: A Log-Scaling Fault Tolerant Agreement Algorithm for a Fault Tolerant MPI. In: Cotronis, Y., Danalis, A., Nikolopoulos, D.S., Dongarra, J. (eds.) EuroMPI 2011. LNCS, vol.\u00a06960, pp. 255\u2013263. Springer, Heidelberg (2011)"},{"key":"24_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"36","DOI":"10.1007\/978-3-540-79561-2_4","volume-title":"OpenMP in a New Era of Parallelism","author":"E. Lusk","year":"2008","unstructured":"Lusk, E., Chan, A.: Early Experiments with the OpenMP\/MPI Hybrid Programming Model. In: Eigenmann, R., de Supinski, B.R. (eds.) IWOMP 2008. LNCS, vol.\u00a05004, pp. 36\u201347. Springer, Heidelberg (2008)"},{"key":"24_CR19","doi-asserted-by":"crossref","unstructured":"Mohan, C., Lindsay, B.: Efficient commit protocols for the tree of processes model of distributed transactions. In: SIGOPS OSR, vol.\u00a019, pp. 40\u201352. ACM (1985)","DOI":"10.1145\/850770.850772"},{"key":"24_CR20","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1007\/978-3-642-19328-6_5","volume-title":"High Performance Computing for Computational Science \u2013 VECPAR 2010","author":"T. Sterling","year":"2011","unstructured":"Sterling, T.: HPC in Phase Change: Towards a New Execution Model. In: Palma, J.M.L.M., Dayd\u00e9, M., Marques, O., Lopes, J.C. (eds.) VECPAR 2010. LNCS, vol.\u00a06449, p. 31. Springer, Heidelberg (2011)"}],"container-title":["Lecture Notes in Computer Science","Recent Advances in the Message Passing Interface"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-33518-1_24.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,5,4]],"date-time":"2021-05-04T12:14:12Z","timestamp":1620130452000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-33518-1_24"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012]]},"ISBN":["9783642335174","9783642335181"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-33518-1_24","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2012]]}}}