{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,11]],"date-time":"2025-11-11T10:35:59Z","timestamp":1762857359773,"version":"build-2065373602"},"publisher-location":"New York, NY, USA","reference-count":25,"publisher":"ACM","funder":[{"name":"United States Department of Energy - Office of Science","award":["DE-SC0024616"],"award-info":[{"award-number":["DE-SC0024616"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,5,4]]},"DOI":"10.1145\/3757348.3757360","type":"proceedings-article","created":{"date-parts":[[2025,11,11]],"date-time":"2025-11-11T10:07:33Z","timestamp":1762855653000},"page":"103-114","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Analyzing a Lifetime of Failures on a Cray XC40 Supercomputer"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0935-5743","authenticated-orcid":false,"given":"Kevin A.","family":"Brown","sequence":"first","affiliation":[{"name":"Mathematics and Computer Science Division, Argonne National Laboratory, Lemont, IL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3716-4693","authenticated-orcid":false,"given":"Tanwi","family":"Mallick","sequence":"additional","affiliation":[{"name":"Mathematics and Computer Science Division, Argonne National Laboratory, Lemont, IL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1047-8724","authenticated-orcid":false,"given":"Zhiling","family":"Lan","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Illinois Chicago, Chicago, IL, USA and Argonne Leadership Computing Facility, Argonne National Laboratory, Lemont, IL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5435-5857","authenticated-orcid":false,"given":"Robert B.","family":"Ross","sequence":"additional","affiliation":[{"name":"Mathematics and Computer Science Division, Argonne National Laboratory, Lemont, IL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8862-9844","authenticated-orcid":false,"given":"Christopher D.","family":"Carothers","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Rensselaer Polytechnic Institute, Troy, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,11,11]]},"reference":[{"key":"e_1_3_3_1_2_2","unstructured":"Bob Alverson Edwin Froese Larry Kaplan and Duncan Roweth. 2012. Cray XC series network. Cray Inc. White Paper WP-Aries01-1112 (2012)."},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.23919\/PanPacific60013.2024.10436446"},{"key":"e_1_3_3_1_4_2","unstructured":"Intel Corporation. 2016. Intel\u00ae 64 and IA-32 Architectures Software Developer\u2019s Manual Volume 3B: System Programming Guide Part 2\". https:\/\/www.intel.com\/content\/www\/us\/en\/developer\/articles\/technical\/intel-sdm.html"},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/DSN.2013.6575356"},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2012.107"},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"crossref","unstructured":"Jiangang Gao Fang Zheng Fengbin Qi Yajun Ding Hongliang Li Hongsheng Lu Wangquan He Hongmei Wei Lifeng Jin Xin Liu et\u00a0al. 2021. Sunway supercomputer architecture towards exascale computing: analysis and practice. Science China Information Sciences 64 4 (2021) 141101.","DOI":"10.1007\/s11432-020-3104-7"},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1145\/3126908.3126937"},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISSREW.2018.00-23"},{"key":"e_1_3_3_1_10_2","unstructured":"Esteban Meneses Xiang Ni Terry Jones and Don Maxwell. 2015. Analyzing the interplay of failures and workload on a leadership-class supercomputer. Computing 2 3 (2015) 4."},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER.2018.00073"},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER.2017.113"},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"crossref","unstructured":"Ju-Won Park Xin Huang and Chul-Ho Lee. 2024. Analyzing and predicting job failures from HPC system log. The Journal of Supercomputing 80 1 (2024) 435\u2013462.","DOI":"10.1007\/s11227-023-05482-y"},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/DSN.2011.5958210"},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/SBAC-PAD.2019.00040"},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"publisher","unstructured":"Bianca Schroeder and Garth\u00a0A Gibson. 2007. Understanding failures in petascale computers. Journal of Physics: Conference Series 78 1 (July 2007) 012022. 10.1088\/1742-6596\/78\/1\/012022","DOI":"10.1088\/1742-6596\/78\/1\/012022"},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"publisher","unstructured":"Bianca Schroeder and Garth\u00a0A. Gibson. 2010. A Large-Scale Study of Failures in High-Performance Computing Systems. IEEE Transactions on Dependable and Secure Computing 7 4 (2010) 337\u2013350. 10.1109\/TDSC.2009.4","DOI":"10.1109\/TDSC.2009.4"},{"key":"e_1_3_3_1_18_2","unstructured":"J Schutkoske. 2014. Cray XC System Level Diagnosability: Commands Utilities and Diagnostic Tools for the Next Generation of HPC Systems. Proceedings of the Cray User Group (CUG) (2014)."},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/CCGrid54584.2022.00081"},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/CCGrid59990.2024.00060"},{"key":"e_1_3_3_1_21_2","doi-asserted-by":"crossref","unstructured":"Marc Snir Robert\u00a0W Wisniewski Jacob\u00a0A Abraham Sarita\u00a0V Adve Saurabh Bagchi Pavan Balaji Jim Belak Pradip Bose Franck Cappello Bill Carlson Andrew\u00a0A Chien Paul Coteus Nathan\u00a0A Debardeleben Pedro\u00a0C Diniz Christian Engelmann Mattan Erez Saverio Fazzari Al Geist Rinku Gupta Fred Johnson Sriram Krishnamoorthy Sven Leyffer Dean Liberty Subhasish Mitra Todd Munson Rob Schreiber Jon Stearley and Eric\u00a0Van Hensbergen. 2014. Addressing failures in exascale computing. Int. J. High Perform. Comput. Appl. 28 2 (May 2014) 129\u2013173.","DOI":"10.1177\/1094342014522573"},{"key":"e_1_3_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/DSN48987.2021.00043"},{"key":"e_1_3_3_1_23_2","doi-asserted-by":"crossref","unstructured":"JunWeon Yoon TaeYoung Hong ChanYeol Park Seo-Young Noh and HeonChang Yu. 2020. Log analysis-based resource and execution time improvement in HPC: a case study. Applied Sciences 10 7 (2020) 2634.","DOI":"10.3390\/app10072634"},{"key":"e_1_3_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/DSN.2009.5270289"},{"key":"e_1_3_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2011.83"},{"key":"e_1_3_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/RAMS.2016.7448082"}],"event":{"name":"CUG 2025: Cray User Group","acronym":"CUG '25","location":"Jersey City USA"},"container-title":["Proceedings of the Cray User Group"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3757348.3757360","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,11]],"date-time":"2025-11-11T10:28:38Z","timestamp":1762856918000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3757348.3757360"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,4]]},"references-count":25,"alternative-id":["10.1145\/3757348.3757360","10.1145\/3757348"],"URL":"https:\/\/doi.org\/10.1145\/3757348.3757360","relation":{},"subject":[],"published":{"date-parts":[[2025,5,4]]},"assertion":[{"value":"2025-11-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}