{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T19:06:04Z","timestamp":1774551964054,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":40,"publisher":"ACM","license":[{"start":{"date-parts":[[2016,11,15]],"date-time":"2016-11-15T00:00:00Z","timestamp":1479168000000},"content-version":"vor","delay-in-days":366,"URL":"http:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CNS-0844983, CNS-1217979, CNS-1422119"],"award-info":[{"award-number":["CNS-0844983, CNS-1217979, CNS-1422119"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000015","name":"U.S. Department of Energy","doi-asserted-by":"publisher","award":["DE- AC02-06CH11357"],"award-info":[{"award-number":["DE- AC02-06CH11357"]}],"id":[{"id":"10.13039\/100000015","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2015,11,15]]},"DOI":"10.1145\/2807591.2807617","type":"proceedings-article","created":{"date-parts":[[2015,10,27]],"date-time":"2015-10-27T09:07:31Z","timestamp":1445936851000},"page":"1-12","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":18,"title":["Fault tolerant MapReduce-MPI for HPC clusters"],"prefix":"10.1145","author":[{"given":"Yanfei","family":"Guo","sequence":"first","affiliation":[{"name":"University of Colorado, Colorado Springs"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wesley","family":"Bland","sequence":"additional","affiliation":[{"name":"Argonne National Laboratory"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pavan","family":"Balaji","sequence":"additional","affiliation":[{"name":"Argonne National Laboratory"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaobo","family":"Zhou","sequence":"additional","affiliation":[{"name":"University of Colorado, Colorado Springs"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2015,11,15]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Apache Hadoop Project. http:\/\/hadoop.apache.org."},{"key":"e_1_3_2_1_2_1","unstructured":"Global view resilience. https:\/\/sites.google.com\/site\/uchicagolssg\/lssg\/research\/gvr."},{"key":"e_1_3_2_1_3_1","unstructured":"MPI: A message-passing interface standard. http:\/\/www.mpi-forum.org\/docs\/mpi-3.0\/mpi30-report.pdf."},{"key":"e_1_3_2_1_4_1","unstructured":"MPICH. http:\/\/www.mpich.org."},{"key":"e_1_3_2_1_5_1","unstructured":"Open MPI with User-Level Failure Mitigation. http:\/\/www.fault-tolerance.org."},{"key":"e_1_3_2_1_6_1","unstructured":"The IOR HPC Benchmark. http:\/\/sourceforge.net\/projects\/ior-sio."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.5555\/2643634.2643636"},{"key":"e_1_3_2_1_8_1","volume-title":"Proc. of IEEE Int'l Symposium on Fault-Tolerant Computing (FTCS)","author":"Barigazzi G.","year":"1983","unstructured":"G. Barigazzi and L. Strigini. Application-transparent setting of recovery points. In Proc. of IEEE Int'l Symposium on Fault-Tolerant Computing (FTCS), 1983."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/2063384.2063427"},{"key":"e_1_3_2_1_10_1","unstructured":"W. Bland G. Bosilca A. Bouteiller T. Herault and J. Dongarra. A proposal for user-level failure mitigation in the mpi-3 standard. In Tech. Rep. Department of Electrical Engineering and Computer Science University of Tennessee 2012."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-32820-6_48"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.5555\/762761.762815"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1177\/1094342009106189"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CloudCom.2011.15"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/1995896.1995923"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.5555\/1251254.1251264"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/DSN.2014.62"},{"key":"e_1_3_2_1_18_1","unstructured":"J. Duell. The design and implementation of berkeley lab's linuxcheckpoint\/restart. In Technical Report LBNL-54941 2002."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.5555\/648137.746632"},{"key":"e_1_3_2_1_20_1","volume-title":"Gang scheduling performance benefits for fine-grain synchronization. Journal of Parallel and Distributed Computing (JPDC), 16:306--318","author":"Feitelson D. G.","year":"1992","unstructured":"D. G. Feitelson and L. Rudolph. Gang scheduling performance benefits for fine-grain synchronization. Journal of Parallel and Distributed Computing (JPDC), 16:306--318, 1992."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.5555\/2535461.2535469"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1177\/1094342004046045"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2014.83"},{"key":"e_1_3_2_1_24_1","volume-title":"Proc. of USENIX\/ACM Int'l Conference on Autonomic Computing (ICAC)","author":"Guo Y.","year":"2013","unstructured":"Y. Guo, J. Rao, and X. Zhou. iShuffle: Improving hadoop performance with Shuffle-on-Write. In Proc. of USENIX\/ACM Int'l Conference on Autonomic Computing (ICAC), 2013."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2007.370605"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/1272996.1273005"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/509593.509647"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/HICSS.1998.656130"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/1807128.1807160"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/2213836.2213840"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2010.18"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.parco.2011.02.004"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.14778\/2536206.2536213"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/121132.121137"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-36949-0_2"},{"key":"e_1_3_2_1_36_1","first-page":"78","article-title":"Understanding failures in petascale computers","author":"Schroeder B.","year":"2007","unstructured":"B. Schroeder and G. A. Gibson. Understanding failures in petascale computers. Journal of Physics: Conference Series, 78, 2007.","journal-title":"Journal of Physics: Conference Series"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2011.180"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/1998582.1998637"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-25821-3_9"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.5555\/230865"}],"event":{"name":"SC15: The International Conference for High Performance Computing, Networking, Storage and Analysis","location":"Austin Texas","acronym":"SC15","sponsor":["SIGHPC ACM Special Interest Group on High Performance Computing, Special Interest Group on High Performance Computing","SIGARCH ACM Special Interest Group on Computer Architecture","IEEE-CS Computer Society"]},"container-title":["Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2807591.2807617","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/2807591.2807617","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/2807591.2807617","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T09:44:27Z","timestamp":1763459067000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2807591.2807617"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,11,15]]},"references-count":40,"alternative-id":["10.1145\/2807591.2807617","10.1145\/2807591"],"URL":"https:\/\/doi.org\/10.1145\/2807591.2807617","relation":{},"subject":[],"published":{"date-parts":[[2015,11,15]]},"assertion":[{"value":"2015-11-15","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}