{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T07:38:50Z","timestamp":1740123530559,"version":"3.37.3"},"reference-count":30,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2015,4,24]],"date-time":"2015-04-24T00:00:00Z","timestamp":1429833600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2015,4,24]],"date-time":"2015-04-24T00:00:00Z","timestamp":1429833600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1017961"],"award-info":[{"award-number":["1017961"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Supercomput"],"published-print":{"date-parts":[[2015,8]]},"DOI":"10.1007\/s11227-015-1422-z","type":"journal-article","created":{"date-parts":[[2015,4,23]],"date-time":"2015-04-23T07:22:39Z","timestamp":1429773759000},"page":"2963-2984","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["A framework for evaluating comprehensive fault resilience mechanisms in numerical programs"],"prefix":"10.1007","volume":"71","author":[{"given":"Sui","family":"Chen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Greg","family":"Bronevetsky","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bin","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marc Casas","family":"Guix","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lu","family":"Peng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2015,4,24]]},"reference":[{"key":"1422_CR1","unstructured":"Gi D, Martinez R, Busquets JV, Baraza JC, Gil PJ (1999) Fault Injection into VHDL models: experimental validation of a fault-tolerant microcomputer system. In: European Dependable Computing Conference, pp 191\u2013208"},{"key":"1422_CR2","unstructured":"(2013) Kulfi fault injector. https:\/\/github.com\/quadpixels\/KULFI"},{"issue":"3","key":"1422_CR3","doi-asserted-by":"publisher","first-page":"305","DOI":"10.1109\/TDMR.2005.853449","volume":"5","author":"RC Baumann","year":"2005","unstructured":"Baumann RC (2005) Radiation-induced soft errors in advanced semiconductor technologies. IEEE Trans. Device Mater. Reliab. 5(3):305\u2013316","journal-title":"IEEE Trans. Device Mater. Reliab."},{"issue":"1","key":"1422_CR4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1561\/2200000016","volume":"3","author":"S Boyd","year":"2011","unstructured":"Boyd S, Parikh N, Chu E, Peleato B, Eckstein J (2011) Distributed optimization and statistical learning via the alternating direction method of multipliers. Found. Trends Mach. Learn. 3(1):1\u2013122","journal-title":"Found. Trends Mach. Learn."},{"key":"1422_CR5","doi-asserted-by":"crossref","unstructured":"Bronevetsky G, de Supinski B (2008) Soft error vulnerability of iterative linear algebra methods. In: International Conference on Supercomputing","DOI":"10.1145\/1375527.1375552"},{"key":"1422_CR6","doi-asserted-by":"crossref","unstructured":"Casas M, de Supinski BR, Bronevetsky G, Schulz M (2012) Fault resilience of the algebraic multi-grid solver. In: International Conference on Supercomputing, pp 91\u2013100","DOI":"10.1145\/2304576.2304590"},{"key":"1422_CR7","doi-asserted-by":"publisher","unstructured":"Chung J, Lee I, Sullivan M, Ryoo JH, Kim DW, Yoon DH, Kaplan L, Erez M (2012) Containment domains: a scalable, efficient, and flexible resilience scheme for exascale systems. In: 2012 international conference for high performance computing, networking, storage and analysis, pp 1\u201311. doi: 10.1109\/SC.2012.36 , http:\/\/ieeexplore.ieee.org\/lpdocs\/epic03\/wrapper.htm?arnumber=6468537","DOI":"10.1109\/SC.2012.36"},{"key":"1422_CR8","doi-asserted-by":"publisher","unstructured":"DeBardeleben N, Blanchard S, Guan Q, Zhang Z, Fu S (2012) Experimental framework for injecting logic errors in a virtual machine to profile applications for soft error resilience. In: Euro-Par 2011: Parallel Processing Workshops, Lecture Notes in Computer Science, vol 7156. Springer, Berlin, pp 282\u2013291. doi: 10.1007\/978-3-642-29740-3_32","DOI":"10.1007\/978-3-642-29740-3_32"},{"key":"1422_CR9","unstructured":"DeBardeleben N, Blanchard S, Sridharan V, Gurumurthi S, Stearley J, Ferreira K (2014) Extra bits on sram and dram errors\u2014more data from the field. In: IEEE Workshop on Silicon Errors in Logic-System Effects (SELSE)"},{"key":"1422_CR10","doi-asserted-by":"publisher","unstructured":"Du P, Luszczek P, Dongarra J (2011) High performance dense linear system solver with soft error resilience. In: 2011 IEEE International Conference on Cluster Computing, pp 272\u2013280. doi: 10.1109\/CLUSTER.2011.38 . http:\/\/ieeexplore.ieee.org\/lpdocs\/epic03\/wrapper.htm?arnumber=6061145","DOI":"10.1109\/CLUSTER.2011.38"},{"key":"1422_CR11","doi-asserted-by":"publisher","unstructured":"Du P, Luszczek P, Dongarra J (2012) High performance dense linear system solver with resilience to multiple soft errors. In: Procedia Computer Science, vol. 9, pp. 216\u2013225. doi: 10.1016\/j.procs.2012.04.023 . http:\/\/www.sciencedirect.com\/science\/article\/pii\/S1877050912001445","DOI":"10.1016\/j.procs.2012.04.023"},{"key":"1422_CR12","doi-asserted-by":"crossref","unstructured":"Ferreira K, Stearley J, James H, Laros I, Oldfield R, Pedretti K, Brightwell R, Riesen R, Bridges PG, Arnold D (2011) Evaluating the viability of process replication reliability for exascale systems. In: Supercomputing","DOI":"10.1145\/2063384.2063443"},{"key":"1422_CR13","unstructured":"Foundation FS (2011) Gnu scientific library\u2014reference manual"},{"issue":"4","key":"1422_CR14","doi-asserted-by":"publisher","first-page":"75","DOI":"10.1109\/2.585157","volume":"30","author":"MC Hsueh","year":"1997","unstructured":"Hsueh MC, Tsai TK, Iyer RK (1997) Fault injection techniques and tools. IEEE Comput 30(4):75\u201382","journal-title":"IEEE Comput"},{"key":"1422_CR15","unstructured":"Huang KH, Abraham JA (2010) Algorithm-based fault tolerance for matrix operations. In: International Conference on Dependable Systems and Networks (DSN), pp 161\u2013170"},{"key":"1422_CR16","unstructured":"ITRS (2013) International technology roadmap for semiconductors. Tech. rep"},{"key":"1422_CR17","doi-asserted-by":"crossref","unstructured":"LaFrieda C, Ipek E, Martinez JF, Manohar R (2007) Utilizing dynamically coupled cores to form a resilient chip multiprocessor. In: International conference on dependable systems and networks (DSN), pp 317\u2013326","DOI":"10.1109\/DSN.2007.100"},{"key":"1422_CR18","doi-asserted-by":"crossref","unstructured":"Lattner C, Adve V (2004) Llvm: a compilation framework for lifelong program analysis and transformation. San Jose, CA, pp 75\u201388","DOI":"10.1109\/CGO.2004.1281665"},{"key":"1422_CR19","doi-asserted-by":"crossref","unstructured":"Li H, Mundy J, Patterson W, Kazazis D, Zaslavsky A, Bahar RI (2007) Thermally-induced soft errors in nanoscale CMOS circuits. In: IEEE international symposium on nanoscale architectures (NANOARCH), pp 62\u201369","DOI":"10.1109\/NANOARCH.2007.4400859"},{"key":"1422_CR20","doi-asserted-by":"crossref","unstructured":"Li ML, Ramachandran P, Karpuzcu UR, Kumar S, Hari S, Adve SV (2009) Accurate microarchitecture-level fault modeling for studying hardware faults. In: International symposiumn on high-performance computer architecture","DOI":"10.1109\/HPCA.2009.4798242"},{"key":"1422_CR21","unstructured":"Li X, Huang MC, Shen K, Chu L (2010) A realistic evaluation of memory hardware errors and software system susceptibility. In: USENIX annual technical conference"},{"key":"1422_CR22","unstructured":"da Lu C, Reed DA (2004) Assessing fault sensitivity in MPI applications. In: Supercomputing"},{"key":"1422_CR23","doi-asserted-by":"crossref","unstructured":"Massengill LW, Bhuva BL, Holman WT, Alles ML, Loveless TD (2012) Technology scaling and soft error reliability. In: IEEE Reliability Physics Symposium (IRPS), pp 3C.1.1\u20133C.1.7","DOI":"10.1109\/IRPS.2012.6241810"},{"issue":"3","key":"1422_CR24","doi-asserted-by":"publisher","first-page":"329","DOI":"10.1109\/TDMR.2005.855685","volume":"5","author":"S Michalak","year":"2005","unstructured":"Michalak S, Harris KW, Hengartner NW, Takala BE, Wender SA (2005) Predicting the Number of Fatal Soft Errors in Los Alamos National Laboratory\u2019s ASC Q Supercomputer. IEEE Trans Device Mater Reliab 5(3):329\u2013335","journal-title":"IEEE Trans Device Mater Reliab"},{"key":"1422_CR25","doi-asserted-by":"publisher","unstructured":"Moody A, Bronevetsky G, Mohror K, De Supinski B (2010) Design, modeling, and evaluation of a scalable multi-level checkpointing system. In: 2010 international conference for high performance computing, networking, storage and analysis (SC), pp 1\u201311. doi: 10.1109\/SC.2010.18","DOI":"10.1109\/SC.2010.18"},{"key":"1422_CR26","unstructured":"Olson WT (2014) Hattrick n-body simulator. http:\/\/code.google.com\/p\/hattrick-nbody"},{"key":"1422_CR27","unstructured":"Reinhardt SK, Mukherjee SS (2000) Transient fault detection via simultaneous multithreading. In: International symposium on computer architecture (ISCA), pp 25\u201336"},{"key":"1422_CR28","unstructured":"Sbragion D (2014) Drc: digital room correction. http:\/\/drc-fir.sourceforge.net\/"},{"key":"1422_CR29","doi-asserted-by":"crossref","unstructured":"Sloan J, Kesler D, Kumar R, Rahimi A (2010) A numerical optimization-based methodology for application robustification: transforming applications for error tolerance. In: International conference on dependable systems and networks (DSN), pp 161\u2013170","DOI":"10.1109\/DSN.2010.5544923"},{"key":"1422_CR30","doi-asserted-by":"crossref","unstructured":"Sloan J, Kumar R, Bronevetsky G (2012) Algorithmic approaches to low overhead fault detection for sparse linear algebra. In: Dependable systems and networks (Section III). http:\/\/ieeexplore.ieee.org\/xpls\/abs_all.jsp?arnumber=6263938","DOI":"10.1109\/DSN.2012.6263938"}],"container-title":["The Journal of Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-015-1422-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11227-015-1422-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-015-1422-z","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-015-1422-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,5]],"date-time":"2022-05-05T22:18:25Z","timestamp":1651789105000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11227-015-1422-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,4,24]]},"references-count":30,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2015,8]]}},"alternative-id":["1422"],"URL":"https:\/\/doi.org\/10.1007\/s11227-015-1422-z","relation":{},"ISSN":["0920-8542","1573-0484"],"issn-type":[{"type":"print","value":"0920-8542"},{"type":"electronic","value":"1573-0484"}],"subject":[],"published":{"date-parts":[[2015,4,24]]},"assertion":[{"value":"24 April 2015","order":1,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}