{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T01:46:31Z","timestamp":1773193591487,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":27,"publisher":"ACM","license":[{"start":{"date-parts":[[2017,5,31]],"date-time":"2017-05-31T00:00:00Z","timestamp":1496188800000},"content-version":"vor","delay-in-days":365,"URL":"http:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CCF-1305622, ACI-1305624, CCF-1513201"],"award-info":[{"award-number":["CCF-1305622, ACI-1305624, CCF-1513201"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2016,5,31]]},"DOI":"10.1145\/2907294.2907315","type":"proceedings-article","created":{"date-parts":[[2016,6,2]],"date-time":"2016-06-02T15:23:42Z","timestamp":1464881022000},"page":"31-42","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":33,"title":["Towards Practical Algorithm Based Fault Tolerance in Dense Linear Algebra"],"prefix":"10.1145","author":[{"given":"Panruo","family":"Wu","sequence":"first","affiliation":[{"name":"University of California Riverside, Riverside, CA, USA"}]},{"given":"Qiang","family":"Guan","sequence":"additional","affiliation":[{"name":"Los Alamos National Laboratory, Los Alamos, NM, USA"}]},{"given":"Nathan","family":"DeBardeleben","sequence":"additional","affiliation":[{"name":"Los Alamos National Laboratory, Los Alamos, NM, USA"}]},{"given":"Sean","family":"Blanchard","sequence":"additional","affiliation":[{"name":"Los Alamos National Laboratory, Los Alamos, NM, USA"}]},{"given":"Dingwen","family":"Tao","sequence":"additional","affiliation":[{"name":"University of California Riverside, Riverside, CA, USA"}]},{"given":"Xin","family":"Liang","sequence":"additional","affiliation":[{"name":"University of California Riverside, Riverside, CA, USA"}]},{"given":"Jieyang","family":"Chen","sequence":"additional","affiliation":[{"name":"University of California Riverside, Riverside, CA, USA"}]},{"given":"Zizhong","family":"Chen","sequence":"additional","affiliation":[{"name":"University of California Riverside, Riverside, CA, USA"}]}],"member":"320","published-online":{"date-parts":[[2016,5,31]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.5555\/1247360.1247401"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","unstructured":"C. Braun S. Halder and H. Wunderlich. A-ABFT: Autonomous Algorithm-Based Fault Tolerance for Matrix Multiplications on Graphics Processing Units. In 2014 44th Annual IEEE\/IFIP International Conference on Dependable Systems and Networks (DSN) pages 443--454 June 2014. 10.1109\/DSN.2014.48","DOI":"10.1109\/DSN.2014.48"},{"key":"e_1_3_2_1_3_1","volume-title":"June","author":"Cappello F.","year":"2014","unstructured":"F. Cappello, A. Geist, W. Gropp, S. Kale, B. Kramer, and M. Snir. Toward Exascale Resilience: 2014 update. Supercomputing frontiers and innovations, 1(1):5--28, June 2014."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/2442516.2442533"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/2493123.2462920"},{"key":"e_1_3_2_1_6_1","volume-title":"Whitepaper","author":"DeBardeleben N.","year":"2009","unstructured":"N. DeBardeleben, J. Laros, J. T. Daly, S. L. Scott, C. Engelmann, and B. Harrod. High-end computing resilience: Analysis of issues facing the HEC community and path-forward for research and development. Whitepaper, 2009."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2012.04.023"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.5555\/2388996.2389102"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASAP.1992.218551"},{"key":"e_1_3_2_1_10_1","volume-title":"Matrix Computations","author":"Golub G. H.","year":"2012","unstructured":"G. H. Golub and C. F. V. Loan. Matrix Computations. JHU Press, Dec. 2012."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2014.128"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/2807591.2807644"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/TC.1984.1676475"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/0743-7315(88)90027-5"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/T-ED.1979.19370"},{"issue":"3","key":"e_1_3_2_1_16_1","first-page":"329","article-title":"Predicting the number of fatal soft errors in Los Alamos National Laboratory's ASC Q supercomputer. Device and Materials Reliability","volume":"5","author":"Michalak S. E.","year":"2005","unstructured":"S. E. Michalak, K. W. Harris, N. W. Hengartner, B. E. Takala, S. Wender, and others. Predicting the number of fatal soft errors in Los Alamos National Laboratory's ASC Q supercomputer. Device and Materials Reliability, IEEE Transactions on, 5(3):329--335, 2005.","journal-title":"IEEE Transactions on"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.5555\/1628854"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/23.556861"},{"key":"e_1_3_2_1_19_1","unstructured":"A. Petitet R. C. Whaley J. Dongarra and A. Cleary. HPL - A Portable Implementation of the High-Performance Linpack Benchmark for Distributed-Memory Computers."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/DSN.2010.5544923"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1177\/1094342014522573"},{"key":"e_1_3_2_1_22_1","first-page":"43","article-title":"Probabilistic logics and the synthesis of reliable organisms from unreliable components","volume":"34","author":"Neumann J. Von","year":"1956","unstructured":"J. Von Neumann. Probabilistic logics and the synthesis of reliable organisms from unreliable components. Automata studies, 34:43--98, 1956.","journal-title":"Automata studies"},{"key":"e_1_3_2_1_23_1","volume-title":"The algebraic eigenvalue problem","author":"Wilkinson J. H.","year":"1965","unstructured":"J. H. Wilkinson, J. H. Wilkinson, and J. H. Wilkinson. The algebraic eigenvalue problem, volume 87. Clarendon Press Oxford, 1965."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/2600212.2600232"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jocs.2013.05.002"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1177\/1094342015578487"},{"key":"e_1_3_2_1_27_1","volume-title":"SER--history, Trends and Challenges: A Guide for Designing with Memory ICs","author":"Ziegler J. F.","year":"2004","unstructured":"J. F. Ziegler and H. Puchner. SER--history, Trends and Challenges: A Guide for Designing with Memory ICs. Cypress, 2004."}],"event":{"name":"HPDC'16: The 25th International Symposium on High-Performance Parallel and Distributed Computing","location":"Kyoto Japan","acronym":"HPDC'16","sponsor":["University of Arizona University of Arizona","SIGARCH ACM Special Interest Group on Computer Architecture","SIGHPC ACM Special Interest Group on High Performance Computing, Special Interest Group on High Performance Computing"]},"container-title":["Proceedings of the 25th ACM International Symposium on High-Performance Parallel and Distributed Computing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2907294.2907315","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/2907294.2907315","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/2907294.2907315","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T09:42:34Z","timestamp":1763458954000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2907294.2907315"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,5,31]]},"references-count":27,"alternative-id":["10.1145\/2907294.2907315","10.1145\/2907294"],"URL":"https:\/\/doi.org\/10.1145\/2907294.2907315","relation":{},"subject":[],"published":{"date-parts":[[2016,5,31]]},"assertion":[{"value":"2016-05-31","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}