{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,27]],"date-time":"2026-09-27T17:24:10Z","timestamp":1790529850983,"version":"4.1.0"},"reference-count":22,"publisher":"Springer Science and Business Media LLC","issue":"12","license":[{"start":{"date-parts":[[2013,5,29]],"date-time":"2013-05-29T00:00:00Z","timestamp":1369785600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Computing"],"published-print":{"date-parts":[[2013,12]]},"DOI":"10.1007\/s00607-013-0331-3","type":"journal-article","created":{"date-parts":[[2013,5,28]],"date-time":"2013-05-28T07:28:13Z","timestamp":1369726093000},"page":"1171-1184","source":"Crossref","is-referenced-by-count":31,"title":["An evaluation of User-Level Failure Mitigation support in MPI"],"prefix":"10.1007","volume":"95","author":[{"given":"Wesley","family":"Bland","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aurelien","family":"Bouteiller","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Thomas","family":"Herault","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Joshua","family":"Hursey","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"George","family":"Bosilca","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jack J.","family":"Dongarra","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2013,5,29]]},"reference":[{"key":"331_CR1","unstructured":"Angskun T, Bosilca G, Dongarra J (2007) Binomial graph: a scalable and faulttolerant logical network topology. In: ISPA07. Number 4742 in LNCS, Springer, pp 471\u2013482"},{"key":"331_CR2","unstructured":"Bland W, Bosilca G, Bouteiller A, Herault T, Dongarra J (2012) A proposal for user-level failure Mitigation in the MPI-3 standard. Department of Electrical Engineering and Computer Science, University of Tennessee"},{"key":"331_CR3","doi-asserted-by":"crossref","unstructured":"Bland W, Bouteiller A, Herault T, Hursey J, Bosilca G, Dongarra JJ (2012) An evaluation of user-level failure mitigation support in MPI. In: Tr\u00e4ff JL, Benkner S, Dongarra JJ (eds) EuroMPI, Lecture Notes in Computer Science, vol 7490, Springer, pp 193\u2013203","DOI":"10.1007\/978-3-642-33518-1_24"},{"key":"331_CR4","doi-asserted-by":"crossref","unstructured":"Bland W, Du P, Bouteiller A, Herault T, Bosilca G, Dongarra JJ (2012) A Checkpoint-on-Failure protocol for algorithm-based recovery in standard MPI. In: 18th Euro-Par, LNCS, vol 7484, Springer, pp 477\u2013489","DOI":"10.1007\/978-3-642-32820-6_48"},{"key":"331_CR5","doi-asserted-by":"crossref","unstructured":"Bosilca G, Bouteiller A, Brunet \u00c9, Cappello F, Dongarra J, Guermouche A, Herault T, Robert Y, Vivien F, Zaidouni D (2012) Unified model for assessing checkpointing protocols at extreme-scale. Tech. report RR-7950, INRIA","DOI":"10.1002\/cpe.3173"},{"key":"331_CR6","unstructured":"Bougeret M, Casanova H, Robert Y, Vivien F, Zaidouni D (2012) Using group replication for resilience on exascale systems. Tech. Rep. 265, LAWNs"},{"issue":"16","key":"331_CR7","first-page":"2196","volume":"22","author":"A Bouteiller","year":"2010","unstructured":"Bouteiller A, Bosilca G, Dongarra J (2010) Redesigning the message logging model for high performance. CCPE 22(16):2196\u20132211","journal-title":"CCPE"},{"key":"331_CR8","doi-asserted-by":"crossref","unstructured":"Buntinas D, Coti C, Herault T, Lemarinier P, Pilard L, Rezmerita A, Rodriguez E, Cappello F (2008) Blocking vs. non-blocking coordinated checkpointing for large-scale fault tolerant MPI protocols. FGCS 24(1):73\u201384. doi: 10.1016\/j.future.2007.02.002","DOI":"10.1016\/j.future.2007.02.002"},{"issue":"4","key":"331_CR9","first-page":"374","volume":"23","author":"F Cappello","year":"2009","unstructured":"Cappello F, Geist A, Gropp B, Kal\u00e9 LV, Kramer B, Snir M (2009) Toward exascale resilience. IJHPCA 23(4):374\u2013388","journal-title":"IJHPCA"},{"key":"331_CR10","doi-asserted-by":"crossref","unstructured":"Davies T, Karlsson C, Liu H, Ding C, Chen Z (2011) High performance linpack benchmark: a fault tolerant implementation without checkpointing. In: 25th ICS, ACM, pp 162\u2013171","DOI":"10.1145\/1995896.1995923"},{"issue":"11","key":"331_CR11","first-page":"3","volume":"25","author":"J Dongarra","year":"2011","unstructured":"Dongarra J, Beckman P et al (2011) The international exascale software roadmap. IJHPCA 25(11):3\u201360","journal-title":"IJHPCA"},{"key":"331_CR12","doi-asserted-by":"crossref","unstructured":"Du P, Bouteiller A et al (2012) Algorithm-based Fault Tolerance for dense matrix factorizations. In: 17th SIGPLAN PPoPP, ACM, pp 225\u2013234","DOI":"10.1145\/2145816.2145845"},{"key":"331_CR13","doi-asserted-by":"crossref","unstructured":"Fagg G, Dongarra J (2000) FT-MPI: Fault Tolerant MPI, supporting dynamic applications in a dynamic world. In: 7th EuroPVM\/MPI, LNCS, vol 1908, Springer, pp 346\u2013353","DOI":"10.1007\/3-540-45255-9_47"},{"key":"331_CR14","doi-asserted-by":"crossref","unstructured":"Gabriel E et al (2004) Open MPI: Goals, concept, and design of a next generation MPI implementation. In: 11th EuroPVM\/MPI, LNCS, vol 3241, Springer, pp 353\u2013377","DOI":"10.1007\/978-3-540-30218-6_19"},{"key":"331_CR15","doi-asserted-by":"crossref","unstructured":"Gropp W, Lusk E (2004) Fault tolerance in Message Passing Interface programs. IJHPCA 18:363\u2013372. doi: 10.1177\/1094342004046045","DOI":"10.1177\/1094342004046045"},{"key":"331_CR16","unstructured":"Hadzilacos V, Toueg S (1993) Distributed systems (2nd edn). In: Fault-tolerant broadcasts and related problems, ACM\/Addison-Wesley, pp 97\u2013145"},{"issue":"6","key":"331_CR17","doi-asserted-by":"crossref","first-page":"518","DOI":"10.1109\/TC.1984.1676475","volume":"100","author":"K Huang","year":"1984","unstructured":"Huang K, Abraham J (1984) Algorithm-based Fault Tolerance for matrix operations. IEEE Trans Comput 100(6):518\u2013528","journal-title":"IEEE Trans Comput"},{"key":"331_CR18","doi-asserted-by":"crossref","unstructured":"Hursey J, Graham RL, Bronevetsky G, Buntinas D, Pritchard H, Solt DG (2011) Run-through stabilization: an MPI proposal for process fault tolerance. In: 18th EuroMPI, LNCS, vol 6690, Springer, pp 329\u2013332","DOI":"10.1007\/978-3-642-24449-0_40"},{"key":"331_CR19","doi-asserted-by":"crossref","unstructured":"Hursey J, Naughton T, Vallee G, Graham RL (2011) A log-scaling fault tolerant agreement algorithm for a fault tolerant MPI. In: 18th EuroMPI, LNCS, vol 6690, Springer, pp 255\u2013263","DOI":"10.1007\/978-3-642-24449-0_29"},{"key":"331_CR20","doi-asserted-by":"crossref","unstructured":"Lusk E, Chan A (2008) Early experiments with the OpenMP\/MPI hybrid programming model. In: 4th IWOMP, LNCS, vol 5004, Springer, pp 36\u201347","DOI":"10.1007\/978-3-540-79561-2_4"},{"key":"331_CR21","doi-asserted-by":"crossref","unstructured":"Mohan C, Lindsay B (1985) Efficient commit protocols for the tree of processes model of distributed transactions. In: SIGOPS OSR, vol 19, ACM, pp 40\u201352","DOI":"10.1145\/850770.850772"},{"key":"331_CR22","doi-asserted-by":"crossref","unstructured":"Sterling T (2011) HPC in phase change: towards a new execution model. In: HPCCS-VECPAR 2010, LNCS, vol 6449, Springer, pp 31\u201331","DOI":"10.1007\/978-3-642-19328-6_5"}],"container-title":["Computing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00607-013-0331-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s00607-013-0331-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00607-013-0331-3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,7,14]],"date-time":"2019-07-14T01:47:28Z","timestamp":1563068848000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s00607-013-0331-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,5,29]]},"references-count":22,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2013,12]]}},"alternative-id":["331"],"URL":"https:\/\/doi.org\/10.1007\/s00607-013-0331-3","relation":{},"ISSN":["0010-485X","1436-5057"],"issn-type":[{"value":"0010-485X","type":"print"},{"value":"1436-5057","type":"electronic"}],"subject":[],"published":{"date-parts":[[2013,5,29]]}}}