{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T22:44:17Z","timestamp":1777675457837,"version":"3.51.4"},"reference-count":26,"publisher":"SAGE Publications","issue":"5","license":[{"start":{"date-parts":[[2017,1,29]],"date-time":"2017-01-29T00:00:00Z","timestamp":1485648000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["The International Journal of High Performance Computing Applications"],"published-print":{"date-parts":[[2018,9]]},"abstract":"<jats:p>We present a domain-decomposition-based preconditioner for the solution of partial differential equations (PDEs) that is resilient to both soft and hard faults. The algorithm reformulates the PDE as a sampling problem, followed by a solution update through data manipulation that is resilient to both soft and hard faults. This reformulation allows us to recast the problem as a set of independent tasks, and exploit data locality to reduce global communication. We discuss two different parallel implementations: (a) a single program multiple data (SPMD) version based on a one-to-one mapping between subdomain and MPI processes responsible for both state and computation; and (b) an asynchronous server\u2013client implementation where all state information is held by the servers and clients are designed solely as computational units. We present a scalability comparison of both implementations under nominal conditions, showing efficiency within ~80% for up to 12,000 cores. We present a resilience analysis under different fault scenarios based on the server\u2013client implementation. This framework provides resiliency to hard faults such that if a client crashes, it stops asking for work, and the servers simply distribute the work among all of the other clients alive. Erroneous subdomain solves (e.g. due to soft faults) appear as corrupted data, which is either rejected if that causes a task to fail, or is seamlessly filtered out during the regression stage through a suitable noise model. Three different types of faults are modeled: hard faults modeling nodes (or clients) crashing; soft faults occurring during the communication of the tasks between server and clients; and soft faults occurring during task execution. We demonstrate the resiliency of the approach for a 2D elliptic PDE, and explore the effect of the faults at various failure rates.<\/jats:p>","DOI":"10.1177\/1094342016684975","type":"journal-article","created":{"date-parts":[[2017,1,30]],"date-time":"2017-01-30T01:01:08Z","timestamp":1485738068000},"page":"658-673","update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":2,"title":["Partial differential equations preconditioner resilient to soft and hard faults"],"prefix":"10.1177","volume":"32","author":[{"given":"F","family":"Rizzi","sequence":"first","affiliation":[{"name":"Sandia National Laboratories, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"K","family":"Morris","sequence":"additional","affiliation":[{"name":"Sandia National Laboratories, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"K","family":"Sargsyan","sequence":"additional","affiliation":[{"name":"Sandia National Laboratories, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"P","family":"Mycek","sequence":"additional","affiliation":[{"name":"Duke University, NC, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"C","family":"Safta","sequence":"additional","affiliation":[{"name":"Sandia National Laboratories, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"O","family":"Le Ma\u00eetre","sequence":"additional","affiliation":[{"name":"Duke University, NC, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"O","family":"Knio","sequence":"additional","affiliation":[{"name":"Duke University, NC, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"B","family":"Debusschere","sequence":"additional","affiliation":[{"name":"Sandia National Laboratories, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"179","published-online":{"date-parts":[[2017,1,29]]},"reference":[{"key":"bibr1-1094342016684975","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW.2014.132"},{"key":"bibr2-1094342016684975","doi-asserted-by":"publisher","DOI":"10.1109\/Co-HPC.2014.4"},{"key":"bibr3-1094342016684975","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2008.12.002"},{"key":"bibr4-1094342016684975","author":"Bridges PG","year":"2012","journal-title":"ArXiv e-prints"},{"key":"bibr5-1094342016684975","doi-asserted-by":"publisher","DOI":"10.1177\/1094342009347767"},{"key":"bibr6-1094342016684975","doi-asserted-by":"crossref","unstructured":"Cappello F, Geist A, Gropp W, Kale S, Kramer B, Snir M (2014) Toward exascale resilience: 2014 update. Supercomputing frontiers and innovations 1(1): 14. Available at http:\/\/superfri.org\/superfri\/article\/view\/14.","DOI":"10.14529\/jsfi140101"},{"key":"bibr7-1094342016684975","volume-title":"Languages and Compilers for Parallel Computing - 26th International Workshop, LCPC 2013","volume":"8664","author":"Cascaval C","year":"2014"},{"key":"bibr8-1094342016684975","doi-asserted-by":"publisher","DOI":"10.1145\/1996130.1996142"},{"key":"bibr9-1094342016684975","doi-asserted-by":"publisher","DOI":"10.1109\/ISPA.2011.50"},{"key":"bibr10-1094342016684975","unstructured":"DOE-ASCR (2011) Exascale programming challenges. Technical report. Available at: http:\/\/science.energy.gov\/~\/media\/ascr\/pdf\/program-documents\/docs\/ProgrammingChallengesWorkshopReport.pdf."},{"key":"bibr11-1094342016684975","unstructured":"DOE-ASCR (2014) Top ten exascale research challenges. Technical report. Available at: http:\/\/science.energy.gov\/~\/media\/ascr\/ascac\/pdf\/meetings\/20140210\/Top10reportFEB14.pdf"},{"key":"bibr12-1094342016684975","doi-asserted-by":"publisher","DOI":"10.1145\/2145816.2145845"},{"key":"bibr13-1094342016684975","doi-asserted-by":"publisher","DOI":"10.1109\/ICPP.2013.114"},{"key":"bibr14-1094342016684975","doi-asserted-by":"crossref","unstructured":"Ferreira K, Riesen R, Ron Oldfield JS, Laros J, Pedretti K, Brightwell R (2011) Keeping checkpoint\/restart viable for exascale systems. Sandia Report SAND2011-6815, Sandia National Labs.","DOI":"10.2172\/1029780"},{"key":"bibr15-1094342016684975","unstructured":"Gray J (1985) Why do computers stop and what can be done about it? Technical report 85.7, Tandem Computers. Available at: http:\/\/www.hpl.hp.com\/techreports\/tandem\/TR-85.7.pdf"},{"key":"bibr16-1094342016684975","unstructured":"Hoemmen M, Heroux MA (2011) Fault-tolerant iterative methods via selective reliability. Technical report, Sandia National Labs."},{"key":"bibr17-1094342016684975","doi-asserted-by":"publisher","DOI":"10.1145\/1353535.1346315"},{"key":"bibr18-1094342016684975","doi-asserted-by":"publisher","DOI":"10.1109\/24.58720"},{"key":"bibr19-1094342016684975","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2010.5470411"},{"key":"bibr20-1094342016684975","unstructured":"Oppenheimer D, Ganapathi A, Patterson DA (2003) Why do internet services fail, and what can be done about it? In: Proceedings of the 4th Conference on USENIX Symposium on Internet Technologies and Systems - Volume 4 (USITS\u201303). Berkeley, CA: USENIX Association. http:\/\/dl.acm.org\/citation.cfm?id=1251460.1251461."},{"key":"bibr21-1094342016684975","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER.2015.103"},{"key":"bibr22-1094342016684975","doi-asserted-by":"publisher","DOI":"10.1109\/DSN.2004.1311948"},{"key":"bibr23-1094342016684975","doi-asserted-by":"publisher","DOI":"10.1137\/15M1014474"},{"key":"bibr24-1094342016684975","doi-asserted-by":"publisher","DOI":"10.1109\/TDSC.2009.4"},{"key":"bibr25-1094342016684975","doi-asserted-by":"publisher","DOI":"10.1109\/DSN.2007.98"},{"key":"bibr26-1094342016684975","doi-asserted-by":"publisher","DOI":"10.1145\/223587.223596"}],"container-title":["The International Journal of High Performance Computing Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/1094342016684975","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.1177\/1094342016684975","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/1094342016684975","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T08:15:35Z","timestamp":1777450535000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.1177\/1094342016684975"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,1,29]]},"references-count":26,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2018,9]]}},"alternative-id":["10.1177\/1094342016684975"],"URL":"https:\/\/doi.org\/10.1177\/1094342016684975","relation":{},"ISSN":["1094-3420","1741-2846"],"issn-type":[{"value":"1094-3420","type":"print"},{"value":"1741-2846","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,1,29]]}}}