{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,20]],"date-time":"2025-09-20T22:10:09Z","timestamp":1758406209125,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":56,"publisher":"ACM","license":[{"start":{"date-parts":[[2011,6,8]],"date-time":"2011-06-08T00:00:00Z","timestamp":1307491200000},"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":[[2011,6,8]]},"DOI":"10.1145\/1996130.1996142","type":"proceedings-article","created":{"date-parts":[[2011,6,28]],"date-time":"2011-06-28T17:34:50Z","timestamp":1309282490000},"page":"73-84","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":74,"title":["Algorithm-based recovery for iterative methods without checkpointing"],"prefix":"10.1145","author":[{"given":"Zizhong","family":"Chen","sequence":"first","affiliation":[{"name":"Colorado School of Mines, Golden, CO, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2011,6,8]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"http:\/\/www.top500.org.  http:\/\/www.top500.org."},{"key":"e_1_3_2_1_2_1","unstructured":"http:\/\/www.nics.tennessee.edu.  http:\/\/www.nics.tennessee.edu."},{"key":"e_1_3_2_1_3_1","unstructured":"http:\/\/geco.mines.edu\/hardware.shtml.  http:\/\/geco.mines.edu\/hardware.shtml."},{"key":"e_1_3_2_1_4_1","unstructured":"http:\/\/wiki.lustre.org.  http:\/\/wiki.lustre.org."},{"key":"e_1_3_2_1_5_1","unstructured":"The International Exascale Software Project. http:\/\/www.exascale.org.  The International Exascale Software Project. http:\/\/www.exascale.org."},{"key":"e_1_3_2_1_6_1","unstructured":"Coordinated Infrastructure for Fault Tolerant Systems. http:\/\/www.mcs.anl.gov\/research\/cifts.  Coordinated Infrastructure for Fault Tolerant Systems. http:\/\/www.mcs.anl.gov\/research\/cifts."},{"key":"e_1_3_2_1_7_1","unstructured":"MPICH-V. http:\/\/mpich-v.lri.fr.  MPICH-V. http:\/\/mpich-v.lri.fr."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/12.9736"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/12.57055"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611971538"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.5555\/266469.266486"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1137\/0613023"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/781498.781513"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/781498.781513"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/1183401.1183405"},{"key":"e_1_3_2_1_17_1","volume-title":"Proceedings of Supercomputing Symposium","author":"Burns G.","year":"1994","unstructured":"G. Burns , R. Daoud , and J. Vaig . LAM: An Open Cluster Environment for MPI . Proceedings of Supercomputing Symposium , 1994 . G. Burns, R. Daoud, and J. Vaig. LAM: An Open Cluster Environment for MPI. Proceedings of Supercomputing Symposium, 1994."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.5555\/762761.762815"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1177\/1094342009106189"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1177\/1094342009347767"},{"key":"e_1_3_2_1_21_1","volume-title":"Checkpointing vs. Migration for Post-Petascale Machines. CoRR abs\/0911.5593","author":"Cappello F.","year":"2009","unstructured":"F. Cappello , H. Casanova , Y. Robert . Checkpointing vs. Migration for Post-Petascale Machines. CoRR abs\/0911.5593 , 2009 . F. Cappello, H. Casanova, Y. Robert. Checkpointing vs. Migration for Post-Petascale Machines. CoRR abs\/0911.5593, 2009."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1007\/11428831_15"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1137\/040616413"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.5555\/1898953.1899028"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2008.58"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2009.42"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/1065944.1065973"},{"key":"e_1_3_2_1_28_1","volume-title":"thesis","author":"Chen Z.","year":"2006","unstructured":"Z. Chen . Scalable techniques for fault tolerant high performance computing. Ph . D. thesis , University of Tennessee , Knoxville, TN, USA , 2006 . Z. Chen. Scalable techniques for fault tolerant high performance computing. Ph.D. thesis, University of Tennessee, Knoxville, TN, USA, 2006."},{"key":"e_1_3_2_1_29_1","volume-title":"Proceedings of the 22nd IEEE International Parallel & Distributed Processing Symposium DPDNS'08 Workshop","author":"Chen Z.","year":"2008","unstructured":"Z. Chen . Extending Algorithm-based Fault Tolerance to Tolerate Fail-stop Failures in High Performance Distributed Environments . Proceedings of the 22nd IEEE International Parallel & Distributed Processing Symposium DPDNS'08 Workshop , Miami, FL, USA, April 14--18 , 2008 . Z. Chen. Extending Algorithm-based Fault Tolerance to Tolerate Fail-stop Failures in High Performance Distributed Environments. Proceedings of the 22nd IEEE International Parallel & Distributed Processing Symposium DPDNS'08 Workshop, Miami, FL, USA, April 14--18, 2008."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/1654059.1654089"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW.2010.5470775"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2010.5470436"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/568522.568525"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-31619-1_8"},{"key":"e_1_3_2_1_37_1","author":"Fagg G. E.","year":"2004","unstructured":"G. E. Fagg , E. Gabriel , Z. Chen ,, T. Angskun , G. Bosilca , J. Pjesivac-Grbovic , and J. J. Dongarra . Process fault-tolerance: Semantics, design and applications for high performance computing. International Journal of High Performance Computing Applications , 2004 . G. E. Fagg, E. Gabriel, Z. Chen,, T. Angskun, G. Bosilca, J. Pjesivac-Grbovic, and J. J. Dongarra. Process fault-tolerance: Semantics, design and applications for high performance computing. International Journal of High Performance Computing Applications, 2004.","journal-title":"International Journal of High Performance Computing Applications"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-30218-6_19"},{"key":"e_1_3_2_1_39_1","volume-title":"CTWatchQuarterly","volume":"3","author":"Gibson G. A.","year":"2007","unstructured":"G. A. Gibson , B. Schroeder , and J. Digney . Failure Tolerance in Petascale Computers . CTWatchQuarterly , Volume 3 , Number 4, November 2007 . G. A. Gibson, B. Schroeder, and J. Digney. Failure Tolerance in Petascale Computers. CTWatchQuarterly, Volume 3, Number 4, November 2007."},{"key":"e_1_3_2_1_40_1","volume-title":"Matrix Computations","author":"Golub G. H.","year":"1989","unstructured":"G. H. Golub and C. F. Van Loan . Matrix Computations . The John Hopkins University Press , 1989 . G. H. Golub and C. F. Van Loan. Matrix Computations. The John Hopkins University Press, 1989."},{"key":"e_1_3_2_1_41_1","volume-title":"Quintana-Ort. Fault-Tolerant High-Performance Matrix Multiplication: Theory and Practice Proceedings of the 2001 International Conference on Dependable Systems and Networks (DSN'01)","author":"Gunnels J.","year":"2001","unstructured":"J. Gunnels , R. van de Geijn, D. Katz, E . Quintana-Ort. Fault-Tolerant High-Performance Matrix Multiplication: Theory and Practice Proceedings of the 2001 International Conference on Dependable Systems and Networks (DSN'01) , Washington, DC, USA , 2001 . J. Gunnels, R. van de Geijn, D. Katz, E. Quintana-Ort. Fault-Tolerant High-Performance Matrix Multiplication: Theory and Practice Proceedings of the 2001 International Conference on Dependable Systems and Networks (DSN'01), Washington, DC, USA, 2001."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPP.2009.20"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/1089014.1089021"},{"key":"e_1_3_2_1_44_1","volume-title":"Fault Tolerance in Large-Scale Scientific Computing. Parallel Processing for Scientific Computing","author":"Hough P.","year":"2006","unstructured":"P. Hough and V. Howle . Fault Tolerance in Large-Scale Scientific Computing. Parallel Processing for Scientific Computing ,M. A. Heroux, P. Raghavan, and H. D. Simon, Eds., SIAM Press , 2006 . P. Hough and V. Howle. Fault Tolerance in Large-Scale Scientific Computing. Parallel Processing for Scientific Computing,M. A. Heroux, P. Raghavan, and H. D. Simon, Eds., SIAM Press, 2006."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/TC.1984.1676475"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1137\/040620394"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1117\/12.936896"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2007.09.004"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1006\/jpdc.1997.1336"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/71.730527"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1002\/(SICI)1097-024X(199709)27:9%3C995::AID-SPE111%3E3.3.CO;2-Y"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/357369.357371"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/DSN.2006.5"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.5555\/645606.660853"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.4330020404"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/12.494100"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.5555\/762761.762822"},{"key":"e_1_3_2_1_59_1","unstructured":"C. Wang F. Mueller C. Engelmann and S. Scot. Job Pause Service under LAM\/MPI  C. Wang F. Mueller C. Engelmann and S. Scot. Job Pause Service under LAM\/MPI"},{"key":"e_1_3_2_1_60_1","volume-title":"Transparent Fault Tolerance. In Proceedings of the 21st IEEE International Parallel and Distributed Processing Symposium","author":"BLCR","year":"2007","unstructured":"BLCR for Transparent Fault Tolerance. In Proceedings of the 21st IEEE International Parallel and Distributed Processing Symposium , March , 2007 , Long Beach, CA, USA. BLCR for Transparent Fault Tolerance. In Proceedings of the 21st IEEE International Parallel and Distributed Processing Symposium, March, 2007, Long Beach, CA, USA."}],"event":{"name":"HPDC '11: The 20th International Symposium on High-Performance Parallel and Distributed Computing","sponsor":["University of Arizona University of Arizona","SIGARCH ACM Special Interest Group on Computer Architecture"],"location":"San Jose California USA","acronym":"HPDC '11"},"container-title":["Proceedings of the 20th international symposium on High performance distributed computing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/1996130.1996142","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/1996130.1996142","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T11:05:55Z","timestamp":1750244755000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/1996130.1996142"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2011,6,8]]},"references-count":56,"alternative-id":["10.1145\/1996130.1996142","10.1145\/1996130"],"URL":"https:\/\/doi.org\/10.1145\/1996130.1996142","relation":{},"subject":[],"published":{"date-parts":[[2011,6,8]]},"assertion":[{"value":"2011-06-08","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}