{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,28]],"date-time":"2025-08-28T12:26:20Z","timestamp":1756383980511,"version":"3.28.0"},"reference-count":21,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"DOI":"10.1109\/clustr.2004.1392609","type":"proceedings-article","created":{"date-parts":[[2005,4,6]],"date-time":"2005-04-06T11:20:51Z","timestamp":1112786451000},"page":"115-124","source":"Crossref","is-referenced-by-count":27,"title":["Improved message logging versus improved coordinated checkpointing for fault tolerant MPI"],"prefix":"10.1109","author":[{"given":"P.","family":"Lemarinier","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"A.","family":"Bouteiller","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"T.","family":"Herault","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"G.","family":"Krawezik","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"F.","family":"Cappello","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"19","article-title":"Netpipe: A network protocol independent performance evaluator","author":"snell","year":"1996","journal-title":"IASTED International Conference on Intelligent Information Management and Systems"},{"key":"17","doi-asserted-by":"publisher","DOI":"10.1109\/FTCS.1999.781033"},{"key":"18","article-title":"The LAM\/MPI checkpoint\/restart framework: System-initiated checkpointing","author":"sankaran","year":"2003","journal-title":"Proceedings LACSI Symposium"},{"key":"15","article-title":"Checkpoint and migration of UNIX processes in the condor distributed processing system","volume":"1346","author":"litzkow","year":"1997","journal-title":"Technical Report Technical Report"},{"key":"16","doi-asserted-by":"publisher","DOI":"10.1109\/RELDIS.1998.740469"},{"key":"13","doi-asserted-by":"publisher","DOI":"10.1016\/0167-8191(96)00024-5"},{"key":"14","first-page":"19","article-title":"An efficient algorithm for causal message logging","author":"lee","year":"1998","journal-title":"17th Symposium on Reliable Distributed Systems (SRDS 1998)"},{"key":"11","article-title":"FT-MPI : Fault tolerant MPI, supporting dynamic applications in a dynamic world","volume":"1908","author":"fagg","year":"2000","journal-title":"7th Euro PVM\/MPI User's Group Meeting2000"},{"key":"12","article-title":"Fault tolerance in MPI programs","author":"gropp","year":"2002","journal-title":"Special issue of the Journal High Performance Computing Applications (IJHPCA"},{"key":"21","doi-asserted-by":"publisher","DOI":"10.1145\/3959.3962"},{"key":"3","doi-asserted-by":"publisher","DOI":"10.1109\/RELDIS.1998.740522"},{"key":"20","doi-asserted-by":"publisher","DOI":"10.1109\/MPIDC.1996.534093"},{"journal-title":"The NAS Parallel Benchmarks 2 0","year":"1995","author":"bailey","key":"2"},{"key":"1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS.1995.500024"},{"key":"10","doi-asserted-by":"publisher","DOI":"10.1145\/568522.568525"},{"key":"7","first-page":"379","article-title":"LAM: An open cluster environment for MPI","author":"burns","year":"1994","journal-title":"Proceedings of Supercomputing Symposium"},{"key":"6","article-title":"Coordinated checkpoint versus message log for fault tolerant MPI","author":"bouteiller","year":"2003","journal-title":"IEEE International Conference on Cluster Computing (CLUSTER 2003)"},{"key":"5","doi-asserted-by":"publisher","DOI":"10.1145\/1048935.1050176"},{"key":"4","article-title":"MPICH-V: Toward a scalable fault tolerant MPI for volatile nodes","author":"bosilca","year":"0","journal-title":"High Performance Networking and Computing (SC2002)"},{"key":"9","doi-asserted-by":"publisher","DOI":"10.1109\/12.142678"},{"key":"8","doi-asserted-by":"publisher","DOI":"10.1145\/214451.214456"}],"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\/01392609.pdf?arnumber=1392609","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,3,14]],"date-time":"2017-03-14T14:47:38Z","timestamp":1489502858000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/1392609\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[null]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/clustr.2004.1392609","relation":{},"subject":[]}}