{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T06:29:17Z","timestamp":1776925757317,"version":"3.51.2"},"publisher-location":"Cham","reference-count":18,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783319143248","type":"print"},{"value":"9783319143255","type":"electronic"}],"license":[{"start":{"date-parts":[[2014,1,1]],"date-time":"2014-01-01T00:00:00Z","timestamp":1388534400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2014]]},"DOI":"10.1007\/978-3-319-14325-5_47","type":"book-chapter","created":{"date-parts":[[2014,12,10]],"date-time":"2014-12-10T08:55:04Z","timestamp":1418201704000},"page":"547-558","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":40,"title":["FlipIt: An LLVM Based Fault Injector for HPC"],"prefix":"10.1007","author":[{"given":"Jon","family":"Calhoun","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Luke","family":"Olson","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marc","family":"Snir","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"issue":"1","key":"47_CR1","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1109\/TDSC.2004.2","volume":"1","author":"A. Avizienis","year":"2004","unstructured":"Avizienis, A., Laprie, J.-C., Randell, B., Landwehr, C.: Basic concepts and taxonomy of dependable and secure computing. IEEE Transactions on Dependable and Secure Computing\u00a01(1), 11\u201333 (2004)","journal-title":"IEEE Transactions on Dependable and Secure Computing"},{"key":"47_CR2","doi-asserted-by":"crossref","unstructured":"Bautista-Gomez, L., Tsuboi, S., Komatitsch, D., Cappello, F., Maruyama, N., Matsuoka, S.: FTI: high performance fault tolerance interface for hybrid systems. In: Proceedings of 2011 International Conference for High Performance Computing, Networking, Storage and Analysis, SC 2011, pp. 32:1\u201332:32. ACM, New York (2011)","DOI":"10.1145\/2063384.2063427"},{"issue":"4","key":"47_CR3","doi-asserted-by":"publisher","first-page":"374","DOI":"10.1177\/1094342009347767","volume":"23","author":"F. Cappello","year":"2009","unstructured":"Cappello, F., Geist, A., Gropp, B., Kale, L., Kramer, B., Snir, M.: Toward exascale resilience. Int. J. High Perform. Comput. Appl.\u00a023(4), 374\u2013388 (2009)","journal-title":"Int. J. High Perform. Comput. Appl."},{"issue":"2","key":"47_CR4","doi-asserted-by":"publisher","first-page":"36","DOI":"10.1109\/32.666826","volume":"24","author":"J. Carreira","year":"1998","unstructured":"Carreira, J., Madeira, H., Silva, J.G.: Xception: a technique for the experimental evaluation of dependability in modern computers. IEEE Transactions on Software Engineering\u00a024(2), 36\u2013125 (1998)","journal-title":"IEEE Transactions on Software Engineering"},{"key":"47_CR5","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1145\/2304576.2304590","volume-title":"Proceedings of the 26th ACM International Conference on Supercomputing, ICS 2012","author":"M. Casas","year":"2012","unstructured":"Casas, M., de Supinski, B.R., Bronevetsky, G., Schulz, M.: Fault resilience of the algebraic multi-grid solver. In: Proceedings of the 26th ACM International Conference on Supercomputing, ICS 2012, pp. 91\u2013100. ACM, New York (2012)"},{"key":"47_CR6","doi-asserted-by":"crossref","unstructured":"de Kruijf, M., Nomura, S., Sankaralingam, K.: Relax: An architectural framework for software recovery of hardware faults. In: Proceedings of the 37th International Symposium on Computer Architecture (ISCA) (2010)","DOI":"10.1145\/1815961.1816026"},{"key":"47_CR7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/SC.2012.49","volume-title":"Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis, SC 2012","author":"D. Fiala","year":"2012","unstructured":"Fiala, D., Mueller, F., Engelmann, C., Riesen, R., Ferreira, K., Brightwell, R.: 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, SC 2012, pp. 1\u201378. IEEE Computer Society Press, Los Alamitos (2012)"},{"key":"47_CR8","unstructured":"Han, S., Rosenberg, H.A., Shin, K.G.: Doctor: An integrated software fault injection environment (1995)"},{"issue":"1","key":"47_CR9","first-page":"494","volume":"46","author":"P.H. Hargrove","year":"2006","unstructured":"Hargrove, P.H., Duell, J.C.: Berkeley lab checkpoint\/restart (BLCR) for linux clusters. Journal of Physics: Conference Series\u00a046(1), 494 (2006)","journal-title":"Journal of Physics: Conference Series"},{"key":"47_CR10","first-page":"51","volume-title":"Proceedings of the 2010 International Workshop on Innovative Architecture for Future Generation High-Performance Processors and Systems, IWIA 2010","author":"P.M. Kogge","year":"2010","unstructured":"Kogge, P.M., La Fratta, P., Vance, M.: [2010] facing the exascale energy wall. In: Proceedings of the 2010 International Workshop on Innovative Architecture for Future Generation High-Performance Processors and Systems, IWIA 2010, pp. 51\u201358. IEEE Computer Society, Washington, DC (2010)"},{"key":"47_CR11","unstructured":"Lattner, C., Adve, V.: LLVM: A Compilation Framework for Lifelong Program Analysis & Transformation. In: Proceedings of the 2004 International Symposium on Code Generation and Optimization (CGO2004), Palo Alto, California (March 2004)"},{"key":"47_CR12","doi-asserted-by":"crossref","unstructured":"Li, D., Vetter, J.S., Yu, W.: Classifying soft error vulnerabilities in extreme-scale scientific applications using a binary instrumentation tool. In: Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis, SC 2012, pp. 57:1\u201357:11. IEEE Computer Society Press, Los Alamitos (2012)","DOI":"10.1109\/SC.2012.29"},{"key":"47_CR13","first-page":"37","volume-title":"Proceedings of the 2004 ACM\/IEEE Conference on Supercomputing, SC 2004","author":"C.-d. Lu","year":"2004","unstructured":"Lu, C.-d., Reed, D.A.: Assessing fault sensitivity in MPI applications. In: Proceedings of the 2004 ACM\/IEEE Conference on Supercomputing, SC 2004, p. 37. IEEE Computer Society, Washington, DC (2004)"},{"key":"47_CR14","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/SC.2012.18","volume-title":"Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis, SC 2012","author":"R. Riesen","year":"2012","unstructured":"Riesen, R., Ferreira, K., Da Silva, D., Lemarinier, P., Arnold, D., Bridges, P.G.: Alleviating scalability issues of checkpointing protocols. In: Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis, SC 2012, pp. 1\u201318. IEEE Computer Society Press, Los Alamitos (2012)"},{"key":"47_CR15","doi-asserted-by":"crossref","unstructured":"Sato, K., Gamblin, T., Moody, A., de Supinski, B.R., Mohror, K., Maruyama, N.: Design and modeling of non-blocking checkpoint system. In: Proceedings of the ATIP\/A*CRC Workshop on Accelerator Technologies for High-Performance Computing: Does Asia Lead the Way?, ATIP 2012, pp. 39:1\u201339:2. A*STAR Computational Resource Centre, Singapore (2012)","DOI":"10.1109\/SC.2012.46"},{"key":"47_CR16","doi-asserted-by":"crossref","unstructured":"Sharma, V.C., Haran, A., Rakamari\u0107, Z., Gopalakrishnan, G.: Towards formal approaches to system resilience. In: Proceedings of the 19th IEEE Pacific Rim International Symposium on Dependable Computing, PRDC (2013)","DOI":"10.1109\/PRDC.2013.14"},{"key":"47_CR17","doi-asserted-by":"crossref","unstructured":"Sridharan, V., Liberty, D.: A study of DRAM failures in the field. In: Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis, SC 2012, pp. 76:1\u201376:11. IEEE Computer Society Press, Los Alamitos (2012)","DOI":"10.1109\/SC.2012.13"},{"key":"47_CR18","doi-asserted-by":"crossref","unstructured":"Stott, D.T., Floering, B., Burke, D., Kalbarczyk, Z., Iyer, R.K.: NFTAPE: A framework for assessing dependability in distributed systems with lightweight fault injectors. In: Proceedings of the IEEE International Computer Performance and Dependability Symposium, pp. 91\u2013100 (2000)","DOI":"10.1109\/IPDS.2000.839467"}],"container-title":["Lecture Notes in Computer Science","Euro-Par 2014: Parallel Processing Workshops"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-14325-5_47","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,14]],"date-time":"2025-05-14T00:19:02Z","timestamp":1747181942000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-14325-5_47"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014]]},"ISBN":["9783319143248","9783319143255"],"references-count":18,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-14325-5_47","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2014]]},"assertion":[{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}