{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,4]],"date-time":"2024-09-04T17:24:56Z","timestamp":1725470696199},"publisher-location":"Berlin, Heidelberg","reference-count":12,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540391104"},{"type":"electronic","value":"9783540391128"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2006]]},"DOI":"10.1007\/11846802_26","type":"book-chapter","created":{"date-parts":[[2006,9,16]],"date-time":"2006-09-16T06:27:41Z","timestamp":1158388061000},"page":"150-157","source":"Crossref","is-referenced-by-count":8,"title":["An Intelligent Management of Fault Tolerance in Cluster Using RADICMPI"],"prefix":"10.1007","author":[{"given":"Angelo","family":"Duarte","sequence":"first","affiliation":[]},{"given":"Dolores","family":"Rexachs","sequence":"additional","affiliation":[]},{"given":"Emilio","family":"Luque","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"26_CR1","doi-asserted-by":"crossref","unstructured":"Agbaria, A.M., Friedman, R.: Starfish: fault-tolerant dynamic MPI programs on clusters of workstations. In: Proceedings of 8th International Symposium on High Performance Distributed Computing, August 1999, pp. 167\u2013176 (1999)","DOI":"10.1109\/HPDC.1999.805295"},{"key":"26_CR2","doi-asserted-by":"crossref","unstructured":"Rao, S., Alvisi, L., Vin, H.: Egida: An extensible toolkit for low-overhead fault-tolerance. In: Proceedings of IEEE Fault-Tolerant Computing Symposium (FTCS-29), Madison, USA (June 1999)","DOI":"10.1109\/FTCS.1999.781033"},{"key":"26_CR3","first-page":"346","volume-title":"Euro PVM\/MPI User\u2019s Group Meeting 2000","author":"G. Fagg","year":"2000","unstructured":"Fagg, G., Dongarra, J.: FT-MPI: Fault tolerant MPI, supporting dynamic applications in a dynamic world. In: Euro PVM\/MPI User\u2019s Group Meeting 2000, Berlin, Germany, pp. 346\u2013353. Springer, Heidelberg (2000)"},{"issue":"4","key":"26_CR4","doi-asserted-by":"publisher","first-page":"371","DOI":"10.1142\/S0129626400000342","volume":"10","author":"S. Louca","year":"2000","unstructured":"Louca, S., Neophytou, N., Lachanas, A., Evripidou, P.: MPI-FT: Portable fault tolerance scheme for MPI. Parallel Processing Letters\u00a010(4), 371\u2013382 (2000)","journal-title":"Parallel Processing Letters"},{"key":"26_CR5","doi-asserted-by":"crossref","unstructured":"Batchu, R., Neelamegam, J., Cui, Z., Beddhua, M., Skjellum, A., Dandass, Y., Apte, M.: MPI\/FT: Architecture and taxonomies for fault-tolerant, message-passing middleware for performance portable parallel computing. In: Proceedings of the 1st IEEE International Symposium of Cluster Computing and the Grid, Melbourne, Australia (2001)","DOI":"10.1109\/CCGRID.2001.923171"},{"key":"26_CR6","doi-asserted-by":"crossref","unstructured":"Bosilca, G., Bouteiller, A., Cappello, F., Djilali, S., Fedak, G., Germain, C., Herault, T., Lemarinier, P., Lodygensky, O., Magniette, F., Neri, V., Selikhov, A.: MPICH-V: Toward a scalable fault tolerant MPI for volatile nodes. In: Proceedings of SuperComputing 2002 (SC 2002) (November 2002)","DOI":"10.1109\/SC.2002.10048"},{"key":"26_CR7","unstructured":"Sankaran, S., Squyres, J.M., Barrett, B., Lumsdaine, A., Duell, J., Hargrove, P., Roman, E.: The LAM\/MPI checkpoint\/restart framework: System-initiated checkpointing. In: Proceedings of LACSI Symposium, Sante Fe, New Mexico, USA (October 2003)"},{"key":"26_CR8","volume-title":"Proceedings of 18th International Parallel and Distributed Processing Symposium","author":"R.T. Aulwes","year":"2004","unstructured":"Aulwes, R.T., Daniel, D.J., Desai, N.N., Graham, R.L., Risinger, L.D., Taylor, M.A., Woodall, T.S., Sukalski, M.W.: Architecture of LA-MPI, a network-fault-tolerant MPI. In: Proceedings of 18th International Parallel and Distributed Processing Symposium. IEEE, Los Alamitos (2004)"},{"key":"26_CR9","doi-asserted-by":"crossref","unstructured":"Gabriel, E., Fagg, G.E., Bosilca, G., Angskun, T., Dongarra, J.J., Squyres, J.M., Sahay, V., Kambadur, P., Barrett, B., 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: Proceedings, 11th European PVM\/MPI Users\u2019 Group Meeting, Budapest, Hungary, September 2004, pp. 97\u2013104 (2004)","DOI":"10.1007\/978-3-540-30218-6_19"},{"issue":"3","key":"26_CR10","doi-asserted-by":"publisher","first-page":"375","DOI":"10.1145\/568522.568525","volume":"34","author":"E.N. Elnozahy","year":"2002","unstructured":"Elnozahy, E.N., Alvisi, L., Wang, Y.M., Johnson, D.B.: A Survey of Rollback-Recovery Protocols in Message-Passing Systems. ACM Computer Survey\u00a034(3), 375\u2013408 (2002)","journal-title":"ACM Computer Survey"},{"key":"26_CR11","doi-asserted-by":"crossref","unstructured":"Kalaiselvi, S., Rajaraman, V.: A Survey of Checkpointing Algorithms for Parallel and Distributed Computers. In: SADHANA:Academic Proceedings in Engineering Sciences, Bangalore, India, October 2000, vol.\u00a025, part 5, pp. 489\u2013510 (2000)","DOI":"10.1007\/BF02703630"},{"key":"26_CR12","unstructured":"Duarte, A., Rexachs, D., Luque, E.: A distributed scheme for fault-tolerance in large Clusters of Workstations. In: Proceedings of Parrallel Computer 2005 (Parco 2005), M\u00e1laga. Spain, September 13-16 (in press, 2005)"}],"container-title":["Lecture Notes in Computer Science","Recent Advances in Parallel Virtual Machine and Message Passing Interface"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/11846802_26.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,11,17]],"date-time":"2020-11-17T19:41:49Z","timestamp":1605642109000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/11846802_26"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2006]]},"ISBN":["9783540391104","9783540391128"],"references-count":12,"URL":"https:\/\/doi.org\/10.1007\/11846802_26","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2006]]}}}