{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,28]],"date-time":"2025-05-28T04:10:52Z","timestamp":1748405452325,"version":"3.41.0"},"reference-count":19,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2003,8,1]],"date-time":"2003-08-01T00:00:00Z","timestamp":1059696000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2003,8,1]],"date-time":"2003-08-01T00:00:00Z","timestamp":1059696000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["International Journal of Parallel Programming"],"published-print":{"date-parts":[[2003,8]]},"DOI":"10.1023\/a:1024504726988","type":"journal-article","created":{"date-parts":[[2003,9,15]],"date-time":"2003-09-15T21:36:35Z","timestamp":1063661795000},"page":"285-303","source":"Crossref","is-referenced-by-count":32,"title":["A Network-Failure-Tolerant Message-Passing System for Terascale Clusters"],"prefix":"10.1007","volume":"31","author":[{"given":"Richard L.","family":"Graham","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sung-Eun","family":"Choi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"David J.","family":"Daniel","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nehal N.","family":"Desai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ronald G.","family":"Minnich","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Craig E.","family":"Rasmussen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"L. Dean","family":"Risinger","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mitchel W.","family":"Sukalski","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"issue":"4","key":"467518_CR1","doi-asserted-by":"crossref","first-page":"277","DOI":"10.1145\/357401.357402","volume":"2","author":"J. H. Saltzer","year":"1984","unstructured":"Jerome H. Saltzer, David P. Reed, and David D. Clark, End-to-End Arguments in System Design, ACM Transactions on Computer Systems, 2(4):277\u2013288 (November 1984).","journal-title":"ACM Transactions on Computer Systems"},{"key":"467518_CR2","doi-asserted-by":"crossref","unstructured":"Jonathan Stone and Craig Partridge, When the CRC and TCP Check-Sum Disagree, SIGCOMM, pp. 309\u2013319 (2000).","DOI":"10.1145\/347059.347561"},{"issue":"1","key":"467518_CR3","first-page":"56","volume":"12","author":"J. J. Dongarra","year":"1996","unstructured":"Jack J. Dongarra and David Walker, MPI: A Standard Message Passing Interface, Supercomputer, 12(1):56\u201368 (January 1996).","journal-title":"Supercomputer"},{"key":"467518_CR4","unstructured":"http:\/\/www.myri.com\/."},{"key":"467518_CR5","unstructured":"http:\/\/www.cs.sandia.gov\/cplant\/."},{"key":"467518_CR6","unstructured":"George Bosilca, Aurelien Bouteiller, Franck Cappello, Samir Djailali, Gilles Fedak, Cecile Germain, Thomas Herault, Pierre Lemarinier, Oleg Lodygensky, Frederic Magniette, Vincent Neri, and Anton Selikhov, MPICH-V: Toward a Scalable Fault Tolerant MPI for Volatile Nodes."},{"key":"467518_CR7","doi-asserted-by":"crossref","unstructured":"Rajeev Thakur, William Gropp, and Ewing Lusk, Users Guide for ROMIO: A High-Performance, Portable MPI-IO Implementation, Mathematics and Computer Science Division, Argonne National Laboratory (October 1997). ANL\/MCS-TM-234.","DOI":"10.2172\/564273"},{"key":"467518_CR8","unstructured":"Georg Stellner, CoCheck: Checkpointing and Process Migration for MPI, Proceedings of the 10th International Parallel Processing Symposium (IPPS '96), Honolulu, Hawaii (1996)."},{"key":"467518_CR9","unstructured":"M. Litzkow, M. Livny, and M. Mutka, Condor\u2013A Hunter of Idle Workstations, 8th International Conference on Distributed Computing System, IEEE Computer Society Press, pp. 108\u2013111 (1988)."},{"key":"467518_CR10","unstructured":"A. Agbaria and R. Friedman, Starfish: Fault-Tolerant Dynamic MPI Programs on Clusters of Workstations, 8th IEEE International Symposium on High Performance Distributed Computing (1999)."},{"issue":"5\u20136","key":"467518_CR11","doi-asserted-by":"crossref","first-page":"595","DOI":"10.1016\/S0167-739X(99)00012-6","volume":"15","author":"G. E. Fagg","year":"1999","unstructured":"Graham E. Fagg, Keith Moore, and Jack J. Dongarra, Scalable Networked Information Processing Environment (SNIPE), Future Generation Computer Systems, 15(5\u20136): 595\u2013605 (1999).","journal-title":"Future Generation Computer Systems"},{"key":"467518_CR12","volume-title":"EuroPVM\/MPI User's Group Meeting 2000","author":"G. Fagg","year":"2000","unstructured":"G. Fagg and J. Dongarra, FT-MPI: Fault Tolerant MPI, Supporting Dynamic Applications in a Dynamic World, EuroPVM\/MPI User's Group Meeting 2000, Springer-Verlag, Berlin, Germany (2000)."},{"key":"467518_CR13","unstructured":"Robbie T. Aulwes, David J. Daniel, Nehal N. Desai, Richard L. Graham, L. Dean Risinger, and Mitchel W. Sukalski, LA-MPI: The Design and Implementation of a Network-Fault-Tolerant MPI for Terascale Clusters, Los Alamos report LA-UR\u201303\u20130929, submitted to SC2003."},{"key":"467518_CR14","doi-asserted-by":"crossref","unstructured":"J. Postel, Transmission Control Protocol, Internet Engineering Task Force, RFC 793 (1981).","DOI":"10.17487\/rfc0793"},{"key":"467518_CR15","volume-title":"TCP\/IP Illustrated, Volume 2; The Implementation","author":"W. R. Stevens","year":"1995","unstructured":"W. R. Stevens, TCP\/IP Illustrated, Volume 2; The Implementation, Addison\u2013Wesley, Reading (1995)."},{"key":"467518_CR16","unstructured":"A. Denis, Variable Reliability Protocol in Globus-Nexus, Technical Report, Information Science Institute (ISI), University of Southern California (1999)."},{"key":"467518_CR17","unstructured":"E. C. Hunke and W. H. Lipscomb, CICE: the Los Alamos Sea Ice Model. Technical Report LA-CC\u201398\u201316, Los Alamos National Laboratory, 1999."},{"key":"467518_CR18","unstructured":"Ron Minnich and Karen Reid, Supermon: High Performance Monitoring for Linux Clusters, The Fifth Annual Linux Showcase and Conference (November 2001)."},{"key":"467518_CR19","doi-asserted-by":"crossref","unstructured":"Erik A. Hendriks, BProc: The Beowulf Distributed Process Space, 16th Annual ACM International Conference on Supercomputing (2002).","DOI":"10.1145\/514211.514212"}],"container-title":["International Journal of Parallel Programming"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1023\/A:1024504726988.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1023\/A:1024504726988\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1023\/A:1024504726988.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,27]],"date-time":"2025-05-27T08:41:15Z","timestamp":1748335275000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1023\/A:1024504726988"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2003,8]]},"references-count":19,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2003,8]]}},"alternative-id":["467518"],"URL":"https:\/\/doi.org\/10.1023\/a:1024504726988","relation":{},"ISSN":["0885-7458","1573-7640"],"issn-type":[{"type":"print","value":"0885-7458"},{"type":"electronic","value":"1573-7640"}],"subject":[],"published":{"date-parts":[[2003,8]]}}}