{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T00:21:08Z","timestamp":1740097268257,"version":"3.37.3"},"publisher-location":"Cham","reference-count":15,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319264271"},{"type":"electronic","value":"9783319264288"}],"license":[{"start":{"date-parts":[[2015,1,1]],"date-time":"2015-01-01T00:00:00Z","timestamp":1420070400000},"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":[[2015]]},"DOI":"10.1007\/978-3-319-26428-8_3","type":"book-chapter","created":{"date-parts":[[2015,12,9]],"date-time":"2015-12-09T00:09:53Z","timestamp":1449619793000},"page":"36-52","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Check-Pointing Approach for Fault Tolerance in OpenSHMEM"],"prefix":"10.1007","author":[{"given":"Pengfei","family":"Hao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Swaroop","family":"Pophale","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pavel","family":"Shamis","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tony","family":"Curtis","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Barbara","family":"Chapman","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2015,12,9]]},"reference":[{"key":"3_CR1","doi-asserted-by":"crossref","unstructured":"Ali, N., Krishnamoorthy, S., Govind, N., Palmer, B.: A redundant communication approach to scalable fault tolerance in PGAS programming models. In: 2011 19th Euromicro International Conference on Parallel, Distributed and Network-Based Processing (PDP), pp. 24\u201331. IEEE (2011)","DOI":"10.1109\/PDP.2011.72"},{"key":"3_CR2","unstructured":"Bland, W., Bosilca, G., Bouteiller, A., Herault, T., Dongarra, J.: A proposal for user-level failure mitigation in the mpi-3 standard. University of Tennessee, Department of Electrical Engineering and Computer Science (2012)"},{"key":"3_CR3","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"193","DOI":"10.1007\/978-3-642-33518-1_24","volume-title":"Recent Advances in the Message Passing Interface","author":"W Bland","year":"2012","unstructured":"Bland, W., Bouteiller, A., Herault, T., Hursey, J., Bosilca, G., Dongarra, J.J.: An evaluation of user-level failure mitigation support in MPI. In: Tr\u00e4ff, J.L., Benkner, S., Dongarra, J.J. (eds.) EuroMPI 2012. LNCS, vol. 7490, pp. 193\u2013203. Springer, Heidelberg (2012)"},{"issue":"4","key":"3_CR4","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. 23(4), 374\u2013388 (2009). \n                      http:\/\/dx.doi.org\/10.1177\/1094342009347767","journal-title":"Int. J. High Perform. Comput. Appl."},{"key":"3_CR5","unstructured":"Community, O.: Openshmem application programming interface (2014). \n                      http:\/\/www.openshmem.org\/"},{"issue":"3","key":"3_CR6","doi-asserted-by":"publisher","first-page":"353","DOI":"10.1177\/1094342004046052","volume":"18","author":"GE Fagg","year":"2004","unstructured":"Fagg, G.E., Dongarra, J.J.: Building and using a fault-tolerant mpi implementation. Int. J. High Perform. Comput. Appl. 18(3), 353\u2013361 (2004)","journal-title":"Int. J. High Perform. Comput. Appl."},{"key":"3_CR7","unstructured":"Hao, P., Shamis, P., Venkata, M.G., Pophale, S., Welch, A., Poole, S., Chapman, B.: Fault tolerance for openshmem. In: Proceedings of the 8th International Conference on Partitioned Global Address Space Programming Models, PGAS 2014, p. 23. ACM, New York (2014). \n                      http:\/\/doi.acm.org\/10.1145\/2676870.2676894"},{"key":"3_CR8","unstructured":"https:\/\/www.olcf.ornl.gov\/titan\/\n                      \n                    : Titan Super-Computer (2013)"},{"key":"3_CR9","doi-asserted-by":"crossref","unstructured":"Hursey, J., Graham, R.L.: Preserving collective performance across process failure for a fault tolerant mpi. In: 2011 IEEE International Symposium on Parallel and Distributed Processing Workshops and Phd Forum (IPDPSW), pp. 1208\u20131215. IEEE (2011)","DOI":"10.1109\/IPDPS.2011.274"},{"key":"3_CR10","unstructured":"Lea, D.: Doug leas malloc (dlmalloc)"},{"key":"3_CR11","unstructured":"Pophale, S.S.: Src: Openshmem library development. In: Proceedings of the International Conference on Supercomputing ICS 2011, p. 374. ACM, New York (2011). \n                      http:\/\/doi.acm.org\/10.1145\/1995896.1995957"},{"key":"3_CR12","unstructured":"Shahzad, F., Kreutzer, M., Zeiser, T., Machado, R., Pieper, A., Hager, G., Wellein, G.: Building a fault tolerant application using the GASPI communication layer. CoRR abs\/1505.04628 (2015). \n                      http:\/\/arxiv.org\/abs\/1505.04628"},{"key":"3_CR13","series-title":"Lecture Notes in Computer Science","first-page":"1","volume-title":"OpenSHMEM and Related Technologies","author":"P Shamis","year":"2014","unstructured":"Shamis, P., Venkata, M.G., Poole, S., Welch, A., Curtis, T.: Designing a high performance openSHMEM implementation using universal common communication substrate as a communication middleware. In: Poole, S., Hernandez, O., Shamis, P. (eds.) OpenSHMEM 2014. LNCS, vol. 8356, pp. 1\u201313. Springer, Heidelberg (2014)"},{"key":"3_CR14","unstructured":"Team, C.: Containment domains c++ api v0.1 March 2014. \n                      http:\/\/lph.ece.utexas.edu\/users\/CDAPI"},{"issue":"9","key":"3_CR15","doi-asserted-by":"publisher","first-page":"1477","DOI":"10.1016\/j.cpc.2010.04.018","volume":"181","author":"M Valiev","year":"2010","unstructured":"Valiev, M., Bylaska, E.J., Govind, N., Kowalski, K., Straatsma, T.P., Van Dam, H.J., Wang, D., Nieplocha, J., Apra, E., Windus, T.L., et al.: NWChem: a comprehensive and scalable open-source solution for large scale molecular simulations. Comput. Phys. Commun. 181(9), 1477\u20131489 (2010)","journal-title":"Comput. Phys. Commun."}],"container-title":["Lecture Notes in Computer Science","OpenSHMEM and Related Technologies. Experiences, Implementations, and Technologies"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-26428-8_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,31]],"date-time":"2019-05-31T16:31:18Z","timestamp":1559320278000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-26428-8_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015]]},"ISBN":["9783319264271","9783319264288"],"references-count":15,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-26428-8_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2015]]},"assertion":[{"value":"9 December 2015","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}