{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T05:14:30Z","timestamp":1755926070566,"version":"3.37.3"},"reference-count":32,"publisher":"Springer Science and Business Media LLC","issue":"11","license":[{"start":{"date-parts":[[2017,4,18]],"date-time":"2017-04-18T00:00:00Z","timestamp":1492473600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2017,4,18]],"date-time":"2017-04-18T00:00:00Z","timestamp":1492473600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/100000083","name":"Directorate for Computer and Information Science and Engineering","doi-asserted-by":"publisher","award":["1527318","1422408"],"award-info":[{"award-number":["1527318","1422408"]}],"id":[{"id":"10.13039\/100000083","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000143","name":"Division of Computing and Communication Foundations","doi-asserted-by":"publisher","award":["1017961"],"award-info":[{"award-number":["1017961"]}],"id":[{"id":"10.13039\/100000143","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Supercomput"],"published-print":{"date-parts":[[2017,11]]},"DOI":"10.1007\/s11227-017-2042-6","type":"journal-article","created":{"date-parts":[[2017,4,18]],"date-time":"2017-04-18T16:27:55Z","timestamp":1492532875000},"page":"4739-4772","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Soft error resilience of Big Data kernels through algorithmic approaches"],"prefix":"10.1007","volume":"73","author":[{"given":"Travis","family":"LeCompte","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Walker","family":"Legrand","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sui","family":"Chen","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":[[2017,4,18]]},"reference":[{"key":"2042_CR1","unstructured":"Christoforides A (2011) Metropolis\u2013Hastings implementation. \n                    https:\/\/github.com\/alexischr\/mh"},{"key":"2042_CR2","unstructured":"IBM\u2019s Big Data Platform and Decision Management (2012) What is big data? \n                    http:\/\/www-01.ibm.com\/software\/data\/bigdata\/what-is-big-data.html"},{"key":"2042_CR3","unstructured":"Gordon R (2013) \n                    http:\/\/math.stackexchange.com\/questions\/346894\/prove-of-the-parsevals-theorem-for-discrete-fourier-transform-dft"},{"key":"2042_CR4","unstructured":"Sharma V, Haran A, Chen S (2013) Kulfi fault injector. \n                    http:\/\/github.com\/quadpixels\/kulfi"},{"key":"2042_CR5","unstructured":"AMPLab at University of California, Berkeley (2014) AMPLab big data benchmark. \n                    https:\/\/amplab.cs.berkeley.edu\/benchmark\/"},{"key":"2042_CR6","unstructured":"Harris M, NVidia (2015) \n                    https:\/\/devblogs.nvidia.com\/parallelforall\/new-features-cuda-7-5\/"},{"key":"2042_CR7","doi-asserted-by":"publisher","unstructured":"Armstrong TG, Ponnekanti V, Borthakur D, Callaghan M (2013) Linkbench: a database benchmark based on the Facebook social graph. In: Proceedings of the 2013 ACM SIGMOD International Conference on Management of Data, ACM, New York, NY, USA, SIGMOD \u201913, pp 1185\u20131196. doi:\n                    10.1145\/2463676.2465296","DOI":"10.1145\/2463676.2465296"},{"key":"2042_CR8","unstructured":"Austin T (1999) Diva: a reliable substrate for deep submicron microarchitecture design. In: Proceedings of the 32nd Annual International Symposium on Microarchitecture (MICRO 1999)"},{"issue":"3","key":"2042_CR9","doi-asserted-by":"publisher","first-page":"285","DOI":"10.1147\/rd.523.0285","volume":"52","author":"C Bender","year":"2008","unstructured":"Bender C, Sanda PN, Kudva P, Mata R, Pokala V, Haraden R, Schallhorn M (2008) Soft-error resilience of the ibm power6 processor input\/output subsystem. IBM J Res Dev 52(3):285\u2013292. doi:\n                    10.1147\/rd.523.0285","journal-title":"IBM J Res Dev"},{"key":"2042_CR10","doi-asserted-by":"publisher","unstructured":"Cappello F, Geist A, Gropp W, Kale S, Kramer B, Snir M (2014) Toward exascale resilience: 2014 update. J Supercomput Front Innov 1(1). doi:\n                    10.14529\/jsfi140101","DOI":"10.14529\/jsfi140101"},{"issue":"8","key":"2042_CR11","doi-asserted-by":"publisher","first-page":"2963","DOI":"10.1007\/s11227-015-1422-z","volume":"71","author":"S Chen","year":"2015","unstructured":"Chen S, Bronevetsky G, Li B, Guix MC, Peng L (2015) A framework for evaluating comprehensive fault resilience mechanisms in numerical programs. J Supercomput 71(8):2963\u20132984. doi:\n                    10.1007\/s11227-015-1422-z","journal-title":"J Supercomput"},{"issue":"4","key":"2042_CR12","doi-asserted-by":"publisher","first-page":"1570","DOI":"10.1007\/s11227-016-1682-2","volume":"72","author":"S Chen","year":"2016","unstructured":"Chen S, Bronevetsky G, Peng L, Li B, Fu X (2016) Soft error resilience in big data kernels through modular analysis. J Supercomput 72(4):1570\u20131596. doi:\n                    10.1007\/s11227-016-1682-2","journal-title":"J Supercomput"},{"key":"2042_CR13","doi-asserted-by":"crossref","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: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis (SC12)","DOI":"10.1109\/SC.2012.36"},{"key":"2042_CR14","doi-asserted-by":"publisher","unstructured":"Collange S, Defour D, Graillat S, Iakymchuk R (2015) Numerical reproducibility for the parallel reduction on multi- and many-core architectures. Parallel Comput 49:83\u201397. doi:\n                    10.1016\/j.parco.2015.09.001\n                    \n                  , \n                    http:\/\/www.sciencedirect.com\/science\/article\/pii\/S0167819115001155","DOI":"10.1016\/j.parco.2015.09.001"},{"key":"2042_CR15","doi-asserted-by":"publisher","unstructured":"Cooper BF, Silberstein A, Tam E, Ramakrishnan R, Sears R (2010) Benchmarking cloud serving systems with ycsb. In: Proceedings of the 1st ACM Symposium on Cloud Computing, ACM, New York, NY, USA, SoCC \u201910, pp 143\u2013154, doi:\n                    10.1145\/1807128.1807152","DOI":"10.1145\/1807128.1807152"},{"key":"2042_CR16","volume-title":"Introduction to Algorithms","author":"TH Cormen","year":"2009","unstructured":"Cormen TH, Leiserson CE, Rivest RL, Stein C (2009) Introduction to Algorithms, 3rd edn. The MIT Press, Cambridge, MA","edition":"3"},{"key":"2042_CR17","doi-asserted-by":"publisher","unstructured":"Ferdman M, Adileh A, Ko\u00e7berber YO, Volos S, Alisafaee M, Jevdjic D, Kaynak C, Popescu AD, Ailamaki A, Falsafi B (2012) Clearing the clouds: a study of emerging scale-out workloads on modern hardware. In: Proceedings of the 17th International Conference on Architectural Support for Programming Languages and Operating Systems, ASPLOS 2012, London, UK, March 3\u20137, 2012, pp 37\u201348. doi:\n                    10.1145\/2150976.2150982","DOI":"10.1145\/2150976.2150982"},{"key":"2042_CR18","unstructured":"Free Software Foundation (2016) GSL\u2014GNU scientific library. \n                    https:\/\/www.gnu.org\/software\/gsl\/"},{"key":"2042_CR19","unstructured":"Gao W, Luo C, Zhan J, Ye H, He X, Wang L, Zhu Y, Tian X (2015) Identifying dwarfs workloads in big data analytics. \n                    http:\/\/arxiv.org\/abs\/1505.06872"},{"key":"2042_CR20","doi-asserted-by":"publisher","unstructured":"Ghazal A, Rabl T, Hu M, Raab F, Poess M, Crolotte A, Jacobsen HA (2013) Bigbench: towards an industry standard benchmark for big data analytics. In: Proceedings of the 2013 ACM SIGMOD International Conference on Management of Data, ACM, New York, NY, USA, SIGMOD \u201913, pp 1197\u20131208. doi:\n                    10.1145\/2463676.2463712","DOI":"10.1145\/2463676.2463712"},{"key":"2042_CR21","unstructured":"Guan Q, Debardeleben N, Blanchard S, Wu P, Monrow L, Chen Z (2016) P-FSEFI: a parallel soft error fault injection framework for parallel applications. In: Proceedings of the 12th Workshop on Silicon Error in Logic-System Effect (SELSE)"},{"key":"2042_CR22","doi-asserted-by":"publisher","unstructured":"Huang S, Huang J, Dai J, Xie T, Huang B (2010) The HiBench benchmark suite: characterization of the MapReduce-based data analysis. In: 2010 IEEE 26th International Conference on Data Engineering Workshops (ICDEW), pp 41\u201351. doi:\n                    10.1109\/ICDEW.2010.5452747","DOI":"10.1109\/ICDEW.20"},{"key":"2042_CR23","unstructured":"Iakymchuk R, Collagne S, Defour D, Graillat S (2015) Exblas: reproducible and accurate BLAS library. In the Proceedings of the Numerical Reproducibility at Exascale (NRE2015) workshop held as part of the Supercomputing Conference (SC15). Austin, TX, USA, November 15-20, 2015. HAL ID: hal-01202396"},{"key":"2042_CR24","unstructured":"ITRS (2013) International technology roadmap for semiconductors. Technical report"},{"key":"2042_CR25","doi-asserted-by":"crossref","unstructured":"Kumar S, Hari S, Adve SV, Naeimi H, Ramachandran P (2012) Relyzer: exploiting application-level fault equivalence to analyze application resiliency to transient faults. In: Proceedings of the 17th ACM International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS 2012)","DOI":"10.1145\/2150976.2150990"},{"key":"2042_CR26","unstructured":"Lattner C, Adve V (2004) LLVM: A compilation framework for lifelong program analysis and transformation. In: Proceedings of the 2004 International Symposium on Code Generation and Optimization (CGO 2004), San Jose, CA, USA"},{"issue":"4","key":"2042_CR27","doi-asserted-by":"publisher","first-page":"1546","DOI":"10.1109\/TVLSI.2015.2452910","volume":"24","author":"W Liu","year":"2016","unstructured":"Liu W, Zhang W, Wang X, Xu J (2016) Distributed sensor network-on-chip for performance optimization of soft-error-tolerant multiprocessor system-on-chip. IEEE Trans Very Large Scale Integr (VLSI) Syst 24(4):1546\u20131559. doi:\n                    10.1109\/TVLSI.2015.2452910","journal-title":"IEEE Trans Very Large Scale Integr (VLSI) Syst"},{"key":"2042_CR28","unstructured":"NVIDIA (2013) Tesla k20 gpu accelerator. \n                    http:\/\/www.nvidia.com\/content\/PDF\/kepler\/Tesla-K20-Passive-BD-06455-001-v07.pdf"},{"issue":"4","key":"2042_CR29","doi-asserted-by":"publisher","first-page":"1617","DOI":"10.1109\/TNS.2015.2447391","volume":"62","author":"F Serrano","year":"2015","unstructured":"Serrano F, Clemente JA, Mecha H (2015) A methodology to emulate single event upsets in flip-flops using FPGAs through partial reconfiguration and instrumentation. IEEE Trans Nucl Sci 62(4):1617\u20131624. doi:\n                    10.1109\/TNS.2015.2447391","journal-title":"IEEE Trans Nucl Sci"},{"key":"2042_CR30","doi-asserted-by":"publisher","unstructured":"Tiwari D, Gupta S, Gallarno G, Rogers J, Maxwell D (2015) Reliability lessons learned from GPU experience with the titan supercomputer at oak ridge leadership computing facility. In: SC15: International Conference for High Performance Computing, Networking, Storage and Analysis, pp 1\u201312. doi:\n                    10.1145\/2807591.2807666","DOI":"10.1145\/2807591.2807666"},{"key":"2042_CR31","doi-asserted-by":"publisher","unstructured":"Wang L, Bertran R, Buyuktosunoglu A, Bose P, Skadron K (2014) Characterization of transient error tolerance for a class of mobile embedded applications. In: 2014 IEEE International Symposium on Workload Characterization (IISWC), pp 74\u201375. doi:\n                    10.1109\/IISWC.2014.6983042","DOI":"10.1109\/IISWC.2014.6983042"},{"key":"2042_CR32","doi-asserted-by":"publisher","unstructured":"Yeh TY, Reinman G, Patel SJ, Faloutsos P (2009) Fool me twice: exploring and exploiting error tolerance in physics-based animation. ACM Trans Graph 29(1):5:1\u20135:11. doi:\n                    10.1145\/1640443.1640448","DOI":"10.1145\/1640443.1640448"}],"container-title":["The Journal of Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11227-017-2042-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-017-2042-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-017-2042-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,5,17]],"date-time":"2020-05-17T08:02:20Z","timestamp":1589702540000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11227-017-2042-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,4,18]]},"references-count":32,"journal-issue":{"issue":"11","published-print":{"date-parts":[[2017,11]]}},"alternative-id":["2042"],"URL":"https:\/\/doi.org\/10.1007\/s11227-017-2042-6","relation":{},"ISSN":["0920-8542","1573-0484"],"issn-type":[{"type":"print","value":"0920-8542"},{"type":"electronic","value":"1573-0484"}],"subject":[],"published":{"date-parts":[[2017,4,18]]},"assertion":[{"value":"18 April 2017","order":1,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}