{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T04:40:48Z","timestamp":1750308048416,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":45,"publisher":"ACM","license":[{"start":{"date-parts":[[2006,6,28]],"date-time":"2006-06-28T00:00:00Z","timestamp":1151452800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2006,6,28]]},"DOI":"10.1145\/1183401.1183433","type":"proceedings-article","created":{"date-parts":[[2007,1,17]],"date-time":"2007-01-17T01:15:56Z","timestamp":1168996556000},"page":"219-228","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":15,"title":["Scalable, fault tolerant membership for MPI tasks on HPC systems"],"prefix":"10.1145","author":[{"given":"Jyothish","family":"Varma","sequence":"first","affiliation":[{"name":"North Carolina State University, Raleigh, NC"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chao","family":"Wang","sequence":"additional","affiliation":[{"name":"North Carolina State University, Raleigh, NC"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Frank","family":"Mueller","sequence":"additional","affiliation":[{"name":"North Carolina State University, Raleigh, NC"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Christian","family":"Engelmann","sequence":"additional","affiliation":[{"name":"Oak Ridge National Laboratory, Oak Ridge, TN"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stephen L.","family":"Scott","sequence":"additional","affiliation":[{"name":"Oak Ridge National Laboratory, Oak Ridge, TN"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2006,6,28]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"http:\/\/www.intel.com\/design\/servers\/ipmi\/index.htm.]]  http:\/\/www.intel.com\/design\/servers\/ipmi\/index.htm.]]"},{"key":"e_1_3_2_1_2_1","unstructured":"http:\/\/www.redbooks.ibm.com\/redbooks\/pdfs\/sg246686.pdf.]]  http:\/\/www.redbooks.ibm.com\/redbooks\/pdfs\/sg246686.pdf.]]"},{"key":"e_1_3_2_1_3_1","volume-title":"http:\/\/www.llnl.gov\/asci\/purple\/benchmarks","author":"The ASCI","year":"2002","unstructured":"The ASCI purple benchmarks. http:\/\/www.llnl.gov\/asci\/purple\/benchmarks , 2002 .]] The ASCI purple benchmarks. http:\/\/www.llnl.gov\/asci\/purple\/benchmarks, 2002.]]"},{"key":"e_1_3_2_1_4_1","volume-title":"Supercomputing","author":"Adiga N.","year":"2002","unstructured":"N. Adiga and et al. An overview of the BlueGene\/L supercomputer . In Supercomputing , Nov. 2002 .]] N. Adiga and et al. An overview of the BlueGene\/L supercomputer. In Supercomputing, Nov. 2002.]]"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/210223.210224"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2004.1302920"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1007\/11557265_25"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/292523.292524"},{"key":"e_1_3_2_1_9_1","volume-title":"Reliable distributed computing using the Isis Toolkit","author":"Birman K. P.","year":"1994","unstructured":"K. P. Birman and R. Van Renesse , editors. Reliable distributed computing using the Isis Toolkit . IEEE Computer Society Press , 1994 .]] K. P. Birman and R. Van Renesse, editors. Reliable distributed computing using the Isis Toolkit. IEEE Computer Society Press, 1994.]]"},{"key":"e_1_3_2_1_10_1","volume-title":"Supercomputing","author":"Bosilca G.","year":"2002","unstructured":"G. Bosilca , A. Boutellier , and F. Cappello . MPICH-V: Toward a scalable fault tolerant MPI for volatile nodes . In Supercomputing , Nov. 2002 .]] G. Bosilca, A. Boutellier, and F. Cappello. MPICH-V: Toward a scalable fault tolerant MPI for volatile nodes. In Supercomputing, Nov. 2002.]]"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/781498.781513"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/782814.782847"},{"key":"e_1_3_2_1_13_1","volume-title":"HPCRI: 1st Workshop on High Performance Computing Reliability Issues, in Proceedings of the 11th International Symposium on High Performance Computer Architecture (HPCA-11)","author":"Chakravorty S.","year":"2005","unstructured":"S. Chakravorty , C. Mendes , and L. Kale . Proactive fault tolerance in large systems . In HPCRI: 1st Workshop on High Performance Computing Reliability Issues, in Proceedings of the 11th International Symposium on High Performance Computer Architecture (HPCA-11) . IEEE Computer Society , 2005 .]] S. Chakravorty, C. Mendes, and L. Kale. Proactive fault tolerance in large systems. In HPCRI: 1st Workshop on High Performance Computing Reliability Issues, in Proceedings of the 11th International Symposium on High Performance Computer Architecture (HPCA-11). IEEE Computer Society, 2005.]]"},{"key":"e_1_3_2_1_14_1","volume-title":"Apr. 23","author":"Chockler G. V.","year":"2001","unstructured":"G. V. Chockler , I. Keidar , and R. Vitenberg . Group communication speci cations: A comprehensive study , Apr. 23 2001 .]] G. V. Chockler, I. Keidar, and R. Vitenberg. Group communication speci cations: A comprehensive study, Apr. 23 2001.]]"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"crossref","unstructured":"F. Cristian. Reaching agreement on processor group membership in synchronous distributed systems June 12 1991.]]  F. Cristian. Reaching agreement on processor group membership in synchronous distributed systems June 12 1991.]]","DOI":"10.1007\/BF01784719"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/240455.240477"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/155332.155333"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/1041680.1041682"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.5555\/838237.838497"},{"key":"e_1_3_2_1_20_1","first-page":"530","volume-title":"International Conference on Distributed Computing Systems","author":"Desai N.","year":"2003","unstructured":"N. Desai and F. Mueller . Scalable distributed conucrrency services for hierarchical locking . In International Conference on Distributed Computing Systems , pages 530 (537, May 2003 .]] N. Desai and F. Mueller. Scalable distributed conucrrency services for hierarchical locking. In International Conference on Distributed Computing Systems, pages 530 (537, May 2003.]]"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2003.10.001"},{"key":"e_1_3_2_1_22_1","volume-title":"Lawrence Berkeley National Laboratory","author":"Duell J.","year":"2000","unstructured":"J. Duell . The design and implementation of berkeley lab's linux checkpoint\/restart. Tr , Lawrence Berkeley National Laboratory , 2000 .]] J. Duell. The design and implementation of berkeley lab's linux checkpoint\/restart. Tr, Lawrence Berkeley National Laboratory, 2000.]]"},{"key":"e_1_3_2_1_23_1","volume-title":"May 20","author":"Duell J.","year":"2002","unstructured":"J. Duell , P. H. Hargrove , and E. S. Roman . Requirements for linux checkpoint\/restart , May 20 2002 .]] J. Duell, P. H. Hargrove, and E. S. Roman. Requirements for linux checkpoint\/restart, May 20 2002.]]"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.5555\/645458.655464"},{"key":"e_1_3_2_1_25_1","first-page":"346","volume-title":"FT-MPI: Fault Tolerant MPI, supporting dynamic applications in a dynamic world","author":"Fagg G. E.","year":"2000","unstructured":"G. E. Fagg and J. J. Dongarra . FT-MPI: Fault Tolerant MPI, supporting dynamic applications in a dynamic world . In Euro PVM\/MPI User's Group Meeting , Lecture Notes in Computer Science, volume 1908 , pages 346 (353, 2000 .]] G. E. Fagg and J. J. Dongarra. FT-MPI: Fault Tolerant MPI, supporting dynamic applications in a dynamic world. In Euro PVM\/MPI User's Group Meeting, Lecture Notes in Computer Science, volume 1908, pages 346 (353, 2000.]]"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-30218-6_19"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1016\/0167-8191(96)00024-5"},{"key":"e_1_3_2_1_29_1","volume-title":"Personal communications","author":"Watson IBM T. J.","year":"2005","unstructured":"IBM T. J. Watson . Personal communications . July 2005 .]] IBM T. J. Watson. Personal communications. July 2005.]]"},{"key":"e_1_3_2_1_30_1","volume-title":"June 12","author":"Keidar I.","year":"2000","unstructured":"I. Keidar . Group communication , June 12 2000 .]] I. Keidar. Group communication, June 12 2000.]]"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.5555\/850927.851766"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/1011767.1011819"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2005.445"},{"key":"e_1_3_2_1_34_1","volume-title":"Aug. 19","author":"Malki D.","year":"1995","unstructured":"D. Malki , D. Dolev , and R. Strong . A framework for partitionable membership service , Aug. 19 1995 .]] D. Malki, D. Dolev, and R. Strong. A framework for partitionable membership service, Aug. 19 1995.]]"},{"key":"e_1_3_2_1_35_1","unstructured":"S. McCanne and S. Floyd. VINT Network Simulator - ns (version 2). http:\/\/www-mash.CS.Berkeley.EDU\/ns\/ Apr. 1999.]]  S. McCanne and S. Floyd. VINT Network Simulator - ns (version 2). http:\/\/www-mash.CS.Berkeley.EDU\/ns\/ Apr. 1999.]]"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1088\/0967-1846\/1\/2\/004"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.5555\/645609.662458"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/1048935.1050172"},{"key":"e_1_3_2_1_39_1","volume-title":"Proceedings, LACSI Symposium","author":"Sankaran S.","year":"2003","unstructured":"S. Sankaran , J. M. Squyres , B. Barrett , A. Lumsdaine , J. Duell , P. Hargrove , and E. Roman . The LAM\/MPI checkpoint\/restart framework: System-initiated checkpointing . In Proceedings, LACSI Symposium , Sante Fe, New Mexico, USA , October 2003 .]] S. Sankaran, J. M. Squyres, B. Barrett, A. Lumsdaine, J. Duell, P. Hargrove, and E. Roman. The LAM\/MPI checkpoint\/restart framework: System-initiated checkpointing. In Proceedings, LACSI Symposium, Sante Fe, New Mexico, USA, October 2003.]]"},{"key":"e_1_3_2_1_40_1","first-page":"379","volume-title":"Proceedings, 10th European PVM\/MPI Users' Group Meeting, number 2840 in Lecture Notes in Computer Science","author":"Squyres J. M.","year":"2003","unstructured":"J. M. Squyres and A. Lumsdaine . A Component Architecture for LAM\/MPI . In Proceedings, 10th European PVM\/MPI Users' Group Meeting, number 2840 in Lecture Notes in Computer Science , pages 379 (387, Venice, Italy, September \/ October 2003 . Springer-Verlag .]] J. M. Squyres and A. Lumsdaine. A Component Architecture for LAM\/MPI. In Proceedings, 10th European PVM\/MPI Users' Group Meeting, number 2840 in Lecture Notes in Computer Science, pages 379 (387, Venice, Italy, September \/ October 2003. Springer-Verlag.]]"},{"key":"e_1_3_2_1_41_1","volume-title":"Proceedings of IPPS '96. The 10th International Parallel Processing Symposium: Honolulu, HI, USA, 15--19 April 1996, pages 526 (531, 1109 Spring Street, Suite 300, Silver Spring, MD 20910, USA","author":"Stellner G.","year":"1996","unstructured":"G. Stellner . CoCheck : checkpointing and process migration for MPI. In IEEE, editor , Proceedings of IPPS '96. The 10th International Parallel Processing Symposium: Honolulu, HI, USA, 15--19 April 1996, pages 526 (531, 1109 Spring Street, Suite 300, Silver Spring, MD 20910, USA , 1996 . IEEE Computer Society Press.]] G. Stellner. CoCheck: checkpointing and process migration for MPI. In IEEE, editor, Proceedings of IPPS '96. The 10th International Parallel Processing Symposium: Honolulu, HI, USA, 15--19 April 1996, pages 526 (531, 1109 Spring Street, Suite 300, Silver Spring, MD 20910, USA, 1996. IEEE Computer Society Press.]]"},{"key":"e_1_3_2_1_42_1","volume-title":"June 18","author":"Toueg S.","year":"1996","unstructured":"S. Toueg and T. D. Chandra . Unreliable failure detectors for reliable distributed systems , June 18 1996 .]] S. Toueg and T. D. Chandra. Unreliable failure detectors for reliable distributed systems, June 18 1996.]]"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-30218-6_20"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-30218-6_43"},{"key":"e_1_3_2_1_45_1","volume-title":"An ef cient topology-adaptive membership protocol for large-scale network services. Technical report","author":"Yang T.","year":"2004","unstructured":"T. Yang , J. Zhou , and L. Chu . An ef cient topology-adaptive membership protocol for large-scale network services. Technical report , University of California , Santa Barbara , Computer Science, June 2004 .]] T. Yang, J. Zhou, and L. Chu. An ef cient topology-adaptive membership protocol for large-scale network services. Technical report, University of California, Santa Barbara, Computer Science, June 2004.]]"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2005.92"}],"event":{"name":"ICS06: International Conference on Supercomputing 2006","sponsor":["ACM Association for Computing Machinery","SIGARCH ACM Special Interest Group on Computer Architecture"],"location":"Cairns Queensland Australia","acronym":"ICS06"},"container-title":["Proceedings of the 20th annual international conference on Supercomputing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/1183401.1183433","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/1183401.1183433","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T15:14:36Z","timestamp":1750259676000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/1183401.1183433"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2006,6,28]]},"references-count":45,"alternative-id":["10.1145\/1183401.1183433","10.1145\/1183401"],"URL":"https:\/\/doi.org\/10.1145\/1183401.1183433","relation":{},"subject":[],"published":{"date-parts":[[2006,6,28]]},"assertion":[{"value":"2006-06-28","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}