{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,11]],"date-time":"2024-09-11T08:19:17Z","timestamp":1726042757705},"publisher-location":"Cham","reference-count":21,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030285951"},{"type":"electronic","value":"9783030285968"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"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":[[2019]]},"DOI":"10.1007\/978-3-030-28596-8_6","type":"book-chapter","created":{"date-parts":[[2019,8,25]],"date-time":"2019-08-25T23:02:45Z","timestamp":1566774165000},"page":"78-93","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Concepts for OpenMP Target Offload Resilience"],"prefix":"10.1007","author":[{"given":"Christian","family":"Engelmann","sequence":"first","affiliation":[]},{"given":"Geoffroy R.","family":"Vall\u00e9e","sequence":"additional","affiliation":[]},{"given":"Swaroop","family":"Pophale","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,8,9]]},"reference":[{"key":"6_CR1","doi-asserted-by":"publisher","unstructured":"Ashraf, R., Hukerikar, S., Engelmann, C.: Pattern-based modeling of multiresilience solutions for high-performance computing. In: Proceedings of the 9th ACM\/SPEC International Conference on Performance Engineering (ICPE) 2018, pp. 80\u201387, April 2018. \n                      https:\/\/doi.org\/10.1145\/3184407.3184421\n                      \n                    , \n                      http:\/\/icpe2018.spec.org","DOI":"10.1145\/3184407.3184421"},{"key":"6_CR2","doi-asserted-by":"publisher","unstructured":"Bautista-Gomez, L., Tsuboi, S., Komatitsch, D., Cappello, F., Maruyama, N., Matsuoka, S.: FTI: high performance fault tolerance interface for hybrid systems. In: International Conference on High Performance Computing, Networking, Storage and Analysis (SC11), pp. 1\u201312, November 2011. \n                      https:\/\/doi.org\/10.1145\/2063384.2063427","DOI":"10.1145\/2063384.2063427"},{"issue":"3","key":"6_CR3","doi-asserted-by":"publisher","first-page":"244","DOI":"10.1177\/1094342013488238","volume":"27","author":"W Bland","year":"2013","unstructured":"Bland, W., Bouteiller, A., Herault, T., Bosilca, G., Dongarra, J.: Post-failure recovery of MPI communication capability: design and rationale. Int. J. High Perform. Comput. Appl. 27(3), 244\u2013254 (2013). \n                      https:\/\/doi.org\/10.1177\/1094342013488238","journal-title":"Int. J. High Perform. Comput. Appl."},{"key":"6_CR4","doi-asserted-by":"publisher","unstructured":"Castain, R.H., Solt, D., Hursey, J., Bouteiller, A.: PMIx: process management for exascale environments. In: European MPI Users\u2019 Group Meeting (EuroMPI 2017), pp. 14:1\u201314:10, September 2017. \n                      https:\/\/doi.org\/10.1145\/3127024.3127027","DOI":"10.1145\/3127024.3127027"},{"key":"6_CR5","doi-asserted-by":"publisher","unstructured":"Chung, J., et al.: Containment domains: a scalable, efficient, and flexible resilience scheme for exascale systems. In: Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis (SC 2012), pp. 58:1\u201358:11. IEEE Computer Society Press, November 2012. \n                      https:\/\/doi.org\/10.1109\/SC.2012.36","DOI":"10.1109\/SC.2012.36"},{"key":"6_CR6","doi-asserted-by":"publisher","unstructured":"Davies, T., Chen, Z.: Correcting soft errors online in LU factorization. In: Proceedings of the 22nd International Symposium on High-performance Parallel and Distributed Computing (HPDC 2013), pp. 167\u2013178 (2013). \n                      https:\/\/doi.org\/10.1145\/2493123.2462920","DOI":"10.1145\/2493123.2462920"},{"key":"6_CR7","doi-asserted-by":"publisher","unstructured":"Elliott, J., Hoemmen, M., Mueller, F.: Evaluating the impact of SDC on the GMRES iterative solver. In: 28th International Parallel and Distributed Processing Symposium (IPDPS 2014), pp. 1193\u20131202, May 2014. \n                      https:\/\/doi.org\/10.1109\/IPDPS.2014.123","DOI":"10.1109\/IPDPS.2014.123"},{"key":"6_CR8","doi-asserted-by":"publisher","unstructured":"Fiala, D., Mueller, F., Engelmann, C., Ferreira, K., Brightwell, R., Riesen, R.: Detection and correction of silent data corruption for large-scale high-performance computing. In: Proceedings of the 25th IEEE\/ACM International Conference on High Performance Computing, Networking, Storage and Analysis (SC 2012), pp. 78:1\u201378:12, November 2012. \n                      https:\/\/doi.org\/10.1109\/SC.2012.49\n                      \n                    , \n                      http:\/\/sc12.supercomputing.org","DOI":"10.1109\/SC.2012.49"},{"key":"6_CR9","doi-asserted-by":"publisher","unstructured":"Gupta, S., Patel, T., Engelmann, C., Tiwari, D.: Failures in large scale systems: long-term measurement, analysis, and implications. In: International Conference on High Performance Computing, Networking, Storage and Analysis (SC 2017), pp. 44:1\u201344:12, November 2017. \n                      https:\/\/doi.org\/10.1145\/3126908.3126937","DOI":"10.1145\/3126908.3126937"},{"key":"6_CR10","doi-asserted-by":"publisher","unstructured":"Hassani, A., Skjellum, A., Brightwell, R.: Design and evaluation of FA-MPI, a transactional resilience scheme for non-blocking MPI. In: 2014 44th Annual IEEE\/IFIP International Conference on Dependable Systems and Networks, pp. 750\u2013755, June 2014. \n                      https:\/\/doi.org\/10.1109\/DSN.2014.78","DOI":"10.1109\/DSN.2014.78"},{"key":"6_CR11","doi-asserted-by":"publisher","unstructured":"Hukerikar, S., Engelmann, C.: Resilience design patterns: a structured approach to resilience at extreme scale (version 1.2). Technical report ORNL\/TM-2017\/745, Oak Ridge National Laboratory, August 2017. \n                      https:\/\/doi.org\/10.2172\/1436045","DOI":"10.2172\/1436045"},{"issue":"12","key":"6_CR12","doi-asserted-by":"publisher","first-page":"4662","DOI":"10.1007\/s11227-016-1752-5","volume":"72","author":"Saurabh Hukerikar","year":"2016","unstructured":"Hukerikar, S., Lucas, R.F.: Rolex: resilience-oriented language extensions for extreme-scale systems. J. Supercomput. 1\u201333 (2016). \n                      https:\/\/doi.org\/10.1007\/s11227-016-1752-5","journal-title":"The Journal of Supercomputing"},{"key":"6_CR13","unstructured":"Meneses, E., Ni, X., Jones, T., Maxwell, D.: Analyzing the interplay of failures and workload on a leadership-class supercomputer. In: Cray User Group Meeting (CUG 2014), March 2014. \n                      https:\/\/cug.org\/proceedings\/cug2015_proceedings\/includes\/files\/pap169.pdf"},{"key":"6_CR14","doi-asserted-by":"publisher","unstructured":"Nie, B., Xue, J., Gupta, S., Engelmann, C., Smirni, E., Tiwari, D.: Characterizing temperature, power, and soft-error behaviors in data center systems: Insights, challenges, and opportunities. In: International Symposium on the Modeling, Analysis, and Simulation of Computer and Telecommunication Systems (MASCOTS 2017), pp. 22\u201331, September 2017. \n                      https:\/\/doi.org\/10.1109\/MASCOTS.2017.12","DOI":"10.1109\/MASCOTS.2017.12"},{"key":"6_CR15","doi-asserted-by":"publisher","unstructured":"Nie, B., et al.: Machine learning models for GPU error prediction in a large scale HPC system. In: International Conference on Dependable Systems and Networks (DSN 2018), pp. 95\u2013106, June 2018. \n                      https:\/\/doi.org\/10.1109\/DSN.2018.00022","DOI":"10.1109\/DSN.2018.00022"},{"key":"6_CR16","doi-asserted-by":"publisher","unstructured":"Pena, A.J., Bland, W., Balaji, P.: VOCL-FT: introducing techniques for efficient soft error coprocessor recovery. In: Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis (SC 2015), pp. 1\u201312, November 2015. \n                      https:\/\/doi.org\/10.1145\/2807591.2807640","DOI":"10.1145\/2807591.2807640"},{"key":"6_CR17","doi-asserted-by":"publisher","first-page":"350","DOI":"10.1016\/j.jpdc.2017.06.010","volume":"109","author":"A Rezaei","year":"2017","unstructured":"Rezaei, A., Mueller, F., Hargrove, P., Roman, E.: DINO: divergent node cloning for sustained redundancy in HPC. J. Parallel Distrib. Comput. 109, 350\u2013362 (2017). \n                      https:\/\/doi.org\/10.1016\/j.jpdc.2017.06.010","journal-title":"J. Parallel Distrib. Comput."},{"key":"6_CR18","doi-asserted-by":"publisher","unstructured":"Sao, P., Vuduc, R.: Self-stabilizing iterative solvers. In: Proceedings of the Workshop on Latest Advances in Scalable Algorithms for Large-Scale Systems (ScalA 2013), pp. 4:1\u20134:8, November 2013. \n                      https:\/\/doi.org\/10.1145\/2530268.2530272","DOI":"10.1145\/2530268.2530272"},{"issue":"2","key":"6_CR19","doi-asserted-by":"publisher","first-page":"129","DOI":"10.1177\/1094342014522573","volume":"28","author":"Marc Snir","year":"2014","unstructured":"Snir, M., et\u00a0al.: Addressing failures in exascale computing. Int. J. High Perform. Comput. Appl. (IJHPCA) 28(2), 127\u2013171 (2014). \n                      https:\/\/doi.org\/10.1177\/1094342014522573\n                      \n                    , \n                      http:\/\/hpc.sagepub.com","journal-title":"The International Journal of High Performance Computing Applications"},{"key":"6_CR20","doi-asserted-by":"publisher","unstructured":"Vazhkudai, S., et al.: The design, deployment, and evaluation of the CORAL pre-exascale systems. In: Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis (SC 2018), pp. 52:1\u201352:12, November 2018. \n                      https:\/\/doi.org\/10.1109\/SC.2018.00055","DOI":"10.1109\/SC.2018.00055"},{"key":"6_CR21","doi-asserted-by":"publisher","unstructured":"Zimmer, C., Maxwell, D., McNally, S., Atchley, S., Vazhkudai, S.S.: GPU age-aware scheduling to improve the reliability of leadership jobs on Titan. In: Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis (SC 2018), pp. 7:1\u20137:11, November 2018. \n                      https:\/\/doi.org\/10.1109\/SC.2018.00010","DOI":"10.1109\/SC.2018.00010"}],"container-title":["Lecture Notes in Computer Science","OpenMP: Conquering the Full Hardware Spectrum"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-28596-8_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,8,25]],"date-time":"2019-08-25T23:33:40Z","timestamp":1566776020000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-28596-8_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030285951","9783030285968"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-28596-8_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"9 August 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"IWOMP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Workshop on OpenMP","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Auckland","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"New Zealand","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2019","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 September 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 September 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iwomp2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/parallel.auckland.ac.nz\/iwomp2019\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"23","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"22","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"96% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.8","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}