{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,19]],"date-time":"2025-03-19T14:00:15Z","timestamp":1742392815428,"version":"3.30.2"},"reference-count":24,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"DOI":"10.1109\/ipdps.2004.1303244","type":"proceedings-article","created":{"date-parts":[[2004,6,10]],"date-time":"2004-06-10T14:19:45Z","timestamp":1086877185000},"page":"212-219","source":"Crossref","is-referenced-by-count":10,"title":["A fault tolerant protocol for massively parallel systems"],"prefix":"10.1109","author":[{"given":"S.","family":"Chakravorty","sequence":"first","affiliation":[]},{"given":"L.V.","family":"Kale","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"19","doi-asserted-by":"publisher","DOI":"10.1145\/357369.357371"},{"key":"22","first-page":"32","article-title":"Error recovery in multicomputers using global checkpoints","author":"tamir","year":"1984","journal-title":"13th International Conference on Parallel Processing"},{"key":"17","article-title":"Sender-based message logging","author":"johnson","year":"1987","journal-title":"5th Annu Int Symp on Fault-Tolerant Computing"},{"journal-title":"Space reclamation for uncordinated checkpointing in message-passing systems","year":"1993","author":"wang","key":"23"},{"key":"18","doi-asserted-by":"crossref","first-page":"175","DOI":"10.7551\/mitpress\/5241.003.0009","article-title":"Charm++: Parallel programming with message-driven objects","author":"kale","year":"1996","journal-title":"Parallel Programming Using C++"},{"key":"24","article-title":"Bigsim: A parallel simulator for performance prediction of extremely large parallel machines","author":"zheng","year":"2004","journal-title":"2004 IPDPS Conference"},{"key":"15","first-page":"346","article-title":"FT-MPI: Fault tolerant MPI, supporting dynamic applications in dynamic world","author":"fagg","year":"2000","journal-title":"Euro PVM\/MPI User's Group Meeting"},{"key":"16","article-title":"Adaptive MPI","author":"huang","year":"2003","journal-title":"LCPC"},{"journal-title":"Manetho Fault Tolerance in Distributed Systems Using Rollback-recovery and Process Replication","year":"1993","author":"elnozahy","key":"13"},{"key":"14","doi-asserted-by":"publisher","DOI":"10.1145\/568522.568525"},{"key":"11","doi-asserted-by":"publisher","DOI":"10.1145\/214451.214456"},{"journal-title":"CLIP A Checkpointing Tool for Message-passing Parallel Programs","year":"1997","author":"chen","key":"12"},{"key":"21","doi-asserted-by":"publisher","DOI":"10.1145\/3959.3962"},{"key":"3","doi-asserted-by":"publisher","DOI":"10.1109\/FTCS.1999.781058"},{"key":"20","doi-asserted-by":"publisher","DOI":"10.1109\/IPPS.1996.508106"},{"key":"2","first-page":"1","article-title":"Understanding the message logging paradigm for masking process crashes","volume":"tr96 1577","author":"alvisi","year":"1996","journal-title":"Technical Report"},{"key":"1","doi-asserted-by":"publisher","DOI":"10.1109\/HPDC.1999.805295"},{"key":"10","doi-asserted-by":"crossref","DOI":"10.1145\/781498.781513","article-title":"Automated application-level checkpointing of mpi programs","author":"bronevetsky","year":"2003","journal-title":"Principles and Practice of Parallel Programming"},{"key":"7","doi-asserted-by":"publisher","DOI":"10.1145\/1048935.1050176"},{"key":"6","article-title":"Toward a scalable fault tolerant mpi for volatile nodes","author":"bosilca","year":"2002","journal-title":"Proceedings of SC 2002"},{"key":"5","doi-asserted-by":"publisher","DOI":"10.1145\/58564.58565"},{"key":"4","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.1988.105471"},{"key":"9","first-page":"207","article-title":"A distributed domino-effect free recovery algorithm","author":"briatico","year":"1984","journal-title":"IEEE International Symposium on Reliability Distributed Software and Databases"},{"key":"8","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTR.2003.1253321"}],"event":{"name":"18th International Parallel and Distributed Processing Symposium, 2004.","location":"Santa Fe, NM, USA"},"container-title":["18th International Parallel and Distributed Processing Symposium, 2004. Proceedings."],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/9132\/28950\/01303244.pdf?arnumber=1303244","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,17]],"date-time":"2024-12-17T14:51:03Z","timestamp":1734447063000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/1303244\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[null]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/ipdps.2004.1303244","relation":{},"subject":[]}}