{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T07:38:49Z","timestamp":1740123529432,"version":"3.37.3"},"reference-count":36,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2021,6,9]],"date-time":"2021-06-09T00:00:00Z","timestamp":1623196800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,6,9]],"date-time":"2021-06-09T00:00:00Z","timestamp":1623196800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"name":"National Key R&D Program of China","award":["2020YFB1506703"],"award-info":[{"award-number":["2020YFB1506703"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62072018","61732002"],"award-info":[{"award-number":["62072018","61732002"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Supercomput"],"published-print":{"date-parts":[[2022,1]]},"DOI":"10.1007\/s11227-021-03892-4","type":"journal-article","created":{"date-parts":[[2021,6,9]],"date-time":"2021-06-09T20:03:51Z","timestamp":1623269031000},"page":"1381-1408","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Efficient detection of silent data corruption in HPC applications with synchronization-free message verification"],"prefix":"10.1007","volume":"78","author":[{"given":"Guozhen","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1101-7927","authenticated-orcid":false,"given":"Hailong","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Depei","family":"Qian","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,6,9]]},"reference":[{"key":"3892_CR1","doi-asserted-by":"publisher","unstructured":"Quinn H, Graham P (2005) Terrestrial-based radiation upsets: a cautionary tale. In: Symposium on field-programmable custom computing machines (FCCM) 2005. IEEE, pp 193\u2013202. https:\/\/doi.org\/10.1109\/FCCM.2005.61","DOI":"10.1109\/FCCM.2005.61"},{"issue":"1","key":"3892_CR2","doi-asserted-by":"publisher","first-page":"193","DOI":"10.1145\/2492101.1555372","volume":"37","author":"B Schroeder","year":"2009","unstructured":"Schroeder B, Pinheiro E, Weber WD (2009) DRAM errors in the wild: a large-scale field study. ACM SIGMETRICS Perform Eval Rev 37(1):193\u2013204","journal-title":"ACM SIGMETRICS Perform Eval Rev"},{"issue":"4","key":"3892_CR3","doi-asserted-by":"publisher","first-page":"111","DOI":"10.1145\/2248487.2150989","volume":"47","author":"AA Hwang","year":"2012","unstructured":"Hwang AA, Stefanovici IA, Schroeder B (2012) Cosmic rays don\u2019t strike twice: understanding the nature of DRAM errors and the implications for system design. ACM SIGPLAN Not 47(4):111\u2013122","journal-title":"ACM SIGPLAN Not"},{"issue":"3","key":"3892_CR4","doi-asserted-by":"publisher","first-page":"1302","DOI":"10.1007\/s11227-013-0884-0","volume":"65","author":"IP Egwutuoha","year":"2013","unstructured":"Egwutuoha IP, Levy D, Selic B, Chen S (2013) A survey of fault tolerance mechanisms and checkpoint\/restart implementations for high performance computing systems. J Supercomput 65(3):1302\u20131326","journal-title":"J Supercomput"},{"issue":"2","key":"3892_CR5","doi-asserted-by":"publisher","first-page":"210","DOI":"10.1177\/1094342013505348","volume":"28","author":"M Bougeret","year":"2014","unstructured":"Bougeret M, Casanova H, Robert Y et al (2014) Using group replication for resilience on exascale systems. Int J High Perform Comput Appl 28(2):210\u2013224","journal-title":"Int J High Perform Comput Appl"},{"key":"3892_CR6","doi-asserted-by":"publisher","unstructured":"Tang X, Zhai J, Qian X et\u00a0al (2018) vSensor: leveraging fixed-workload snippets of programs for performance variance detection. In: Proceedings of the 23rd ACM SIGPLAN symposium on principles and practice of parallel programming, pp 124\u2013136. https:\/\/doi.org\/10.1145\/3178487.3178497","DOI":"10.1145\/3178487.3178497"},{"key":"3892_CR7","unstructured":"NAS Parallel Benchmarks Team (2021) NAS Parallel Benchmarks. https:\/\/www.nas.nasa.gov\/publications\/npb.html"},{"key":"3892_CR8","unstructured":"Dongarra J, Luszczek P, Heroux M (2021) HPCG. https:\/\/www.hpcg-benchmark.org\/index.html"},{"key":"3892_CR9","unstructured":"Innovative Computing Laboratory (2021) University of Tennessee. HPCC. http:\/\/icl.cs.utk.edu\/hpcc\/"},{"key":"3892_CR10","doi-asserted-by":"publisher","unstructured":"Sridharan V, Liberty D (2012) A study of DRAM failures in the field. In: Proceedings of the international conference on high performance computing, networking, storage and analysis. IEEE, pp 1\u201311. https:\/\/doi.org\/10.1109\/SC.2012.13","DOI":"10.1109\/SC.2012.13"},{"key":"3892_CR11","doi-asserted-by":"publisher","unstructured":"Li S, Chen K, Hsieh M Y, et\u00a0al (2011) System implications of memory reliability in exascale computing. In: Proceedings of 2011 international conference for high performance computing, networking, storage and analysis. IEEE, pp 1\u201312. https:\/\/doi.org\/10.1145\/2063384.2063445","DOI":"10.1145\/2063384.2063445"},{"issue":"1","key":"3892_CR12","first-page":"20","volume":"60","author":"P Somnath","year":"2010","unstructured":"Somnath P, Fang C, Xinmiao Z, Swarup B (2010) Reliability-driven ECC allocation for multiple bit error resilience in processor cache. IEEE Trans Comput 60(1):20\u201334","journal-title":"IEEE Trans Comput"},{"issue":"6","key":"3892_CR13","doi-asserted-by":"publisher","first-page":"518","DOI":"10.1109\/TC.1984.1676475","volume":"100","author":"H Kuang-Hua","year":"1984","unstructured":"Kuang-Hua H, Abraham Jacob A (1984) Algorithm-based fault tolerance for matrix operations. IEEE Trans Comput 100(6):518\u2013528","journal-title":"IEEE Trans Comput"},{"issue":"1","key":"3892_CR14","doi-asserted-by":"publisher","first-page":"37","DOI":"10.4018\/jghpc.2012010103","volume":"4","author":"H Hodjat","year":"2012","unstructured":"Hodjat H, Abbas V, Hassan MSA (2012) Analysis and evaluation of a new algorithm based fault tolerance for computing systems. Int J Grid High Perform Comput 4(1):37\u201351","journal-title":"Int J Grid High Perform Comput"},{"issue":"7","key":"3892_CR15","doi-asserted-by":"publisher","first-page":"849","DOI":"10.1109\/12.293265","volume":"43","author":"W Sying-Jyan","year":"1994","unstructured":"Sying-Jyan W, Jha Niraj K (1994) Algorithm-based fault tolerance for FFT networks. IEEE Trans Comput 43(7):849\u2013854","journal-title":"IEEE Trans Comput"},{"key":"3892_CR16","doi-asserted-by":"publisher","unstructured":"Bautista-Gomez L, Cappello F (2015) Exploiting spatial smoothness in hpc applications to detect silent data corruption. In: IEEE international symposium on IEEE international conference on high performance computing & communications. IEEE, pp 128\u2013133. https:\/\/doi.org\/10.1109\/HPCC-CSS-ICESS.2015.9","DOI":"10.1109\/HPCC-CSS-ICESS.2015.9"},{"key":"3892_CR17","doi-asserted-by":"publisher","unstructured":"Bautista-Gomez L, Cappello F (2015) Detecting silent data corruption for extreme-scale MPI applications. In: Proceedings of the 22nd European MPI Users\u2019 Group Meeting, pp 1\u201310. https:\/\/doi.org\/10.1145\/2802658.2802665","DOI":"10.1145\/2802658.2802665"},{"issue":"8","key":"3892_CR18","doi-asserted-by":"publisher","first-page":"381","DOI":"10.1145\/2692916.2555279","volume":"49","author":"B-G Leonardo","year":"2014","unstructured":"Leonardo B-G, Franck C (2014) Detecting silent data corruption through data dynamic monitoring for scientific applications. ACM SIGPLAN Not 49(8):381\u2013382","journal-title":"ACM SIGPLAN Not"},{"key":"3892_CR19","doi-asserted-by":"publisher","unstructured":"Chen C, Eisenhauer G, Wolf M et al (2018) LADR: low-cost application-level detector for reducing silent output corruptions. In: Proceedings of the 27th international symposium on high-performance parallel and distributed computing, pp 156\u2013167.\u00a0https:\/\/doi.org\/10.1145\/3208040.3208043","DOI":"10.1145\/3208040.3208043"},{"key":"3892_CR20","doi-asserted-by":"publisher","unstructured":"Berrocal E, Bautista-Gomez L, Di S et\u00a0al (2015) Lightweight silent data corruption detection based on runtime data analysis for HPC applications. In: Proceedings of the 24th International Symposium on High-Performance Parallel and Distributed Computing, pp 275\u2013278. https:\/\/doi.org\/10.1145\/2749246.2749253","DOI":"10.1145\/2749246.2749253"},{"issue":"12","key":"3892_CR21","doi-asserted-by":"publisher","first-page":"3642","DOI":"10.1109\/TPDS.2017.2735971","volume":"28","author":"E Berrocal","year":"2017","unstructured":"Berrocal E, Bautista-Gomez L, Di S et al (2017) Toward general software level silent data corruption detection for parallel applications. IEEE Trans Parallel Distrib Syst 28(12):3642\u20133655","journal-title":"IEEE Trans Parallel Distrib Syst"},{"key":"3892_CR22","doi-asserted-by":"publisher","unstructured":"Berrocal E, Bautista-Gomez L, Di S et\u00a0al (2016) Exploring partial replication to improve lightweight silent data corruption detection for HPC applications. In: Proceedings of european conference on parallel processing. Springer, Cham, pp 419\u2013430. https:\/\/doi.org\/10.1007\/978-3-319-43659-3_313","DOI":"10.1007\/978-3-319-43659-3_313"},{"key":"3892_CR23","doi-asserted-by":"publisher","unstructured":"Subasi O, Di S, Balaprakash P et\u00a0al (2017) MACORD: online adaptive machine learning framework for silent error detection. In: Proceedings of 2017 IEEE international conference on cluster computing (CLUSTER). IEEE, pp 717\u2013724. https:\/\/doi.org\/10.1109\/CLUSTER.2017.128","DOI":"10.1109\/CLUSTER.2017.128"},{"key":"3892_CR24","doi-asserted-by":"publisher","unstructured":"Di S, Berrocal E, Cappello F (2015) An efficient silent data corruption detection method with error-feedback control and even sampling for hpc applications. In: Proceedings of the 15th IEEE\/ACM International Symposium on Cluster, Cloud, and Grid Computing. IEEE, pp 271\u2013280. https:\/\/doi.org\/10.1109\/CCGrid.2015.17","DOI":"10.1109\/CCGrid.2015.17"},{"issue":"10","key":"3892_CR25","doi-asserted-by":"publisher","first-page":"2809","DOI":"10.1109\/TPDS.2016.2517639","volume":"27","author":"D Sheng","year":"2016","unstructured":"Sheng D, Franck C (2016) Adaptive impact-driven detection of silent data corruption for hpc applications. IEEE Trans Parallel Distrib Syst 27(10):2809\u20132823","journal-title":"IEEE Trans Parallel Distrib Syst"},{"key":"3892_CR26","doi-asserted-by":"publisher","unstructured":"Li S, Di S, Zhao K, Liang X, Chen Z, Cappello F (2020) Towards end-to-end SDC detection for HPC applications equipped with lossy compression. In: 2020 IEEE international conference on cluster computing (CLUSTER). IEEE, pp 326\u2013336. https:\/\/doi.org\/10.1109\/CLUSTER49012.2020.00043","DOI":"10.1109\/CLUSTER49012.2020.00043"},{"key":"3892_CR27","doi-asserted-by":"publisher","unstructured":"Ferreira K, Riesen R, Oldfield R, Stearley J, Laros J, Pedretti K, Brightwell R (2011) rMPI: increasing fault resiliency in a message-passing environment, Sandia National Laboratories, Albuquerque, NM, Tech. Rep. SAND2011-2488. https:\/\/doi.org\/10.2172\/1012733","DOI":"10.2172\/1012733"},{"key":"3892_CR28","doi-asserted-by":"publisher","first-page":"124","DOI":"10.1007\/978-3-642-03770-2_19","volume-title":"European parallel virtual machine\/message passing interface users\u2019 group meeting","author":"PL Troy","year":"2009","unstructured":"Troy PL, Rakhi A, Edgar G, Jaspal SS (2009) Volpexmpi: an MPI library for execution of parallel applications on volatile nodes. European parallel virtual machine\/message passing interface users\u2019 group meeting. Springer, Berlin, Heidelberg, pp 124\u2013133. https:\/\/doi.org\/10.1007\/978-3-642-03770-2_19"},{"key":"3892_CR29","doi-asserted-by":"publisher","unstructured":"Wang Z, Yang X, Zhou Y (2010) MMPI: a scalable fault tolerance mechanism for MPI large scale parallel computing. In: 2010 10th IEEE international conference on computer and information technology. IEEE, pp 1251\u20131256. https:\/\/doi.org\/10.1109\/CIT.2010.226","DOI":"10.1109\/CIT.2010.226"},{"key":"3892_CR30","doi-asserted-by":"crossref","unstructured":"Engelmann C, Bhm S (2011) Redundant execution of HPC applications with MR-MPI. In: Proceedings of the 10th IASTED international conference on parallel and distributed computing and networks (PDCN), pp 15\u201317","DOI":"10.2316\/P.2011.719-031"},{"key":"3892_CR31","doi-asserted-by":"publisher","unstructured":"Fiala D, Mueller F, Engelmann C, Riesen R, Ferreira KB (2012) Detection and correction of silent data corruption for large-scale high-performance computing. In: Proceedings of the international conference on high performance computing, networking, storage and analysis. IEEE, pp 1\u201312. https:\/\/doi.org\/10.1109\/SC.2012.49","DOI":"10.1109\/SC.2012.49"},{"key":"3892_CR32","doi-asserted-by":"publisher","unstructured":"P\u00e9rez D, Ropars T, Meneses E (2021) On the detection of silent data corruptions in HPC applications using redundant multi-threading. Euro-par: 2020 parallel processing workshops. Nature Publishing Group, 12480, 290. https:\/\/doi.org\/10.1007\/2F978-3-030-71593-9_23","DOI":"10.1007\/2F978-3-030-71593-9_23"},{"key":"3892_CR33","doi-asserted-by":"publisher","unstructured":"Mitropoulou K, Porpodas V, Jones TM (2016) COMET: communication-optimised multi-threaded error-detection technique. In: 2016 International conference on compliers, architectures, and synthesis of embedded systems (CASES). IEEE, pp 1\u201310. https:\/\/doi.org\/10.1145\/2968455.2968508","DOI":"10.1145\/2968455.2968508"},{"issue":"4","key":"3892_CR34","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2687651","volume":"11","author":"L Porter","year":"2015","unstructured":"Porter L, Laurenzano MA, Tiwari A et al (2015) Making the most of SMT in HPC: system-and application-level perspectives. ACM Trans Archit Code Optim (TACO) 11(4):1\u201326","journal-title":"ACM Trans Archit Code Optim (TACO)"},{"issue":"6","key":"3892_CR35","doi-asserted-by":"publisher","first-page":"2231","DOI":"10.1109\/23.903758","volume":"47","author":"P Cheynet","year":"2000","unstructured":"Cheynet P, Nicolescu B, Velazco R et al (2000) Experimentally evaluating an automatic approach for generating safety-critical software with respect to transient errors. IEEE Trans Nucl Sci 47(6):2231\u20132236","journal-title":"IEEE Trans Nucl Sci"},{"issue":"4","key":"3892_CR36","doi-asserted-by":"publisher","first-page":"403","DOI":"10.1177\/1094342014532297","volume":"29","author":"AR Benson","year":"2015","unstructured":"Benson AR, Schmit S, Schreiber R (2015) Silent error detection in numerical time-stepping schemes. Int J High Perform Comput Appl 29(4):403\u2013421","journal-title":"Int J High Perform Comput Appl"}],"container-title":["The Journal of Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-021-03892-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11227-021-03892-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-021-03892-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,4]],"date-time":"2022-01-04T12:24:51Z","timestamp":1641299091000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11227-021-03892-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,9]]},"references-count":36,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2022,1]]}},"alternative-id":["3892"],"URL":"https:\/\/doi.org\/10.1007\/s11227-021-03892-4","relation":{},"ISSN":["0920-8542","1573-0484"],"issn-type":[{"type":"print","value":"0920-8542"},{"type":"electronic","value":"1573-0484"}],"subject":[],"published":{"date-parts":[[2021,6,9]]},"assertion":[{"value":"13 May 2021","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 June 2021","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}