{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T17:28:12Z","timestamp":1764782892160,"version":"3.32.0"},"reference-count":27,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"DOI":"10.1109\/clustr.2004.1392606","type":"proceedings-article","created":{"date-parts":[[2005,4,6]],"date-time":"2005-04-06T15:20:51Z","timestamp":1112800851000},"page":"93-103","source":"Crossref","is-referenced-by-count":37,"title":["FTC-Charm++: an in-memory checkpoint-based fault tolerant runtime for Charm++ and MPI"],"prefix":"10.1109","author":[{"family":"Gengbin Zheng","sequence":"first","affiliation":[]},{"family":"Lixia Shi","sequence":"additional","affiliation":[]},{"given":"L.V.","family":"Kale","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"19","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":"17","article-title":"The virtualization model of parallel programming : Runtime optimizations and the state of art","author":"kale?","year":"2002","journal-title":"LACSI 2002"},{"key":"18","first-page":"1152","article-title":"Run-time support for adaptive load balancing","volume":"1800","author":"kale","year":"2000","journal-title":"Lecture Notes in Computer Science Proceedings of 4th Workshop on Runtime Systems for Parallel Programming (RTSPP) Cancun - Mexico"},{"key":"15","article-title":"Adaptive MPI","author":"huang","year":"2003","journal-title":"Proceedings of the I6th International Workshop on Languages and Compilers for Parallel Computing (LCPC 03)"},{"key":"16","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2004.1303335"},{"key":"13","doi-asserted-by":"publisher","DOI":"10.1145\/568522.568525"},{"key":"14","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 Croup Meeting"},{"journal-title":"Egida - Lightweight Fault-tolerance for Distributed Systems","year":"2003","key":"11"},{"journal-title":"Manetho Fault Tolerance in Distributed Systems Using Rollback-recovery and Process Replication","year":"1993","author":"elnozahy","key":"12"},{"key":"21","doi-asserted-by":"crossref","DOI":"10.1109\/FTCS.1994.315631","article-title":"Faster checkpointing with n+1 parity","author":"plank","year":"1994","journal-title":"The 23rd Annual International Symposium on Fault-Tolerant Computing"},{"key":"20","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.665"},{"key":"22","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.1975.6312842"},{"key":"23","doi-asserted-by":"publisher","DOI":"10.1109\/IPPS.1996.508106"},{"key":"24","doi-asserted-by":"publisher","DOI":"10.1145\/3959.3962"},{"key":"25","first-page":"32","article-title":"Error recovery in multicomputers using global checkpoints","author":"tamir","year":"1984","journal-title":"13th International Conference on Parallel Processing"},{"journal-title":"Space Reclamation for Uncoordinated Check-pointing in Message-passing Systems","year":"1993","author":"wang","key":"26"},{"key":"27","article-title":"Bigsim: A parallel simulator for performance prediction of extremely large parallel machines","author":"zheng","year":"2004","journal-title":"Proc 18th Int Parallel Distributed Processing Symp (IPDPS)"},{"key":"3","doi-asserted-by":"publisher","DOI":"10.1109\/FTCS.1999.781058"},{"key":"2","doi-asserted-by":"publisher","DOI":"10.1109\/HPDC.1999.805295"},{"journal-title":"CLIP A Checkpointing Tool for Message-passing Parallel Programs","year":"1997","author":"chen","key":"10"},{"journal-title":"Supercomputing 2002 Technical Papers","article-title":"An overview of the bluegene\/L supercomputer","year":"2002","key":"1"},{"key":"7","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":"6","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":"5","doi-asserted-by":"publisher","DOI":"10.1145\/1048935.1050176"},{"key":"4","article-title":"Toward a scalable fault tolerant mpi for volatile nodes","author":"bosilca","year":"2002","journal-title":"Proceedings of SC 2002"},{"key":"9","doi-asserted-by":"publisher","DOI":"10.1145\/214451.214456"},{"key":"8","article-title":"A fault tolerant protocol for massively parallel machines","author":"chakravorty","year":"2004","journal-title":"FTPDS Workshop at IPDPS'2004"}],"event":{"name":"2004 IEEE International Conference on Cluster Computing","acronym":"CLUSTR-04","location":"San Diego, CA, USA"},"container-title":["2004 IEEE International Conference on Cluster Computing (IEEE Cat. No.04EX935)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/9584\/30302\/01392606.pdf?arnumber=1392606","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,31]],"date-time":"2024-12-31T01:50:51Z","timestamp":1735609851000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/1392606\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[null]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/clustr.2004.1392606","relation":{},"subject":[]}}