{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T15:44:34Z","timestamp":1759333474957,"version":"3.40.3"},"publisher-location":"Cham","reference-count":25,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030293994"},{"type":"electronic","value":"9783030294007"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019]]},"DOI":"10.1007\/978-3-030-29400-7_25","type":"book-chapter","created":{"date-parts":[[2019,8,18]],"date-time":"2019-08-18T23:02:41Z","timestamp":1566169361000},"page":"346-360","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["Enabling Resilience in Asynchronous Many-Task Programming Models"],"prefix":"10.1007","author":[{"given":"Sri Raj","family":"Paul","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Akihiro","family":"Hayashi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nicole","family":"Slattengren","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hemanth","family":"Kolla","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Matthew","family":"Whitlock","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Seonmyeong","family":"Bak","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Keita","family":"Teranishi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jackson","family":"Mayo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vivek","family":"Sarkar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,8,13]]},"reference":[{"key":"25_CR1","unstructured":"HClib Resilience Branch. https:\/\/github.com\/srirajpaul\/hclib\/tree\/feature\/resilience. Accessed 14 June 2019"},{"issue":"2","key":"25_CR2","doi-asserted-by":"publisher","first-page":"187","DOI":"10.1002\/cpe.1631","volume":"23","author":"C Augonnet","year":"2011","unstructured":"Augonnet, C., et al.: StarPU: a unified platform for task scheduling on heterogeneous multicore architectures. Concurr. Comput. Pract. Exp. 23(2), 187\u2013198 (2011). https:\/\/doi.org\/10.1002\/cpe.1631","journal-title":"Concurr. Comput. Pract. Exp."},{"key":"25_CR3","doi-asserted-by":"publisher","unstructured":"Bauer, M., et al.: Legion: expressing locality and independence with logical regions. In: Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis, SC 2012, pp. 66:1\u201366:11 (2012). https:\/\/doi.org\/10.1109\/SC.2012.71","DOI":"10.1109\/SC.2012.71"},{"key":"25_CR4","unstructured":"Bennett, J., et al.: ASC ATDM level 2 milestone #5325: asynchronous many-task runtime system analysis and assessment for next generation platform. Technical report SAND2015-8312, Sandia National Laboratories, September 2015"},{"issue":"6","key":"25_CR5","doi-asserted-by":"publisher","first-page":"36","DOI":"10.1109\/MCSE.2013.98","volume":"15","author":"G Bosilca","year":"2013","unstructured":"Bosilca, G., et al.: PaRSEC: exploiting heterogeneity to enhance scalability. Comput. Sci. Eng. 15(6), 36\u201345 (2013). https:\/\/doi.org\/10.1109\/MCSE.2013.98","journal-title":"Comput. Sci. Eng."},{"key":"25_CR6","doi-asserted-by":"publisher","unstructured":"Cao, C., et al.: Design for a soft error resilient dynamic task-based runtime. In: 2015 IEEE International Parallel and Distributed Processing Symposium, pp. 765\u2013774, May 2015. https:\/\/doi.org\/10.1109\/IPDPS.2015.81","DOI":"10.1109\/IPDPS.2015.81"},{"issue":"1","key":"25_CR7","doi-asserted-by":"publisher","first-page":"5","DOI":"10.14529\/jsfi140101","volume":"1","author":"F Cappello","year":"2014","unstructured":"Cappello, F., et al.: Toward exascale resilience: 2014 update. Supercomput. Front. Innov. Int. J. 1(1), 5\u201328 (2014). https:\/\/doi.org\/10.14529\/jsfi140101","journal-title":"Supercomput. Front. Innov. Int. J."},{"key":"25_CR8","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 (2012). https:\/\/doi.org\/10.1109\/SC.2012.36","DOI":"10.1109\/SC.2012.36"},{"key":"25_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"601","DOI":"10.1007\/978-3-319-14313-2_51","volume-title":"Euro-Par 2014: Parallel Processing Workshops","author":"A Fern\u00e1ndez","year":"2014","unstructured":"Fern\u00e1ndez, A., Beltran, V., Martorell, X., Badia, R.M., Ayguad\u00e9, E., Labarta, J.: Task-based programming with OmpSs and its application. In: Lopes, L., et al. (eds.) Euro-Par 2014. LNCS, vol. 8806, pp. 601\u2013612. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-14313-2_51"},{"key":"25_CR10","doi-asserted-by":"publisher","unstructured":"Georgakoudis, G., et al.: Refine: realistic fault injection via compiler-based instrumentation for accuracy, portability and speed. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, SC 2017, pp. 29:1\u201329:14 (2017). https:\/\/doi.org\/10.1145\/3126908.3126972","DOI":"10.1145\/3126908.3126972"},{"key":"25_CR11","doi-asserted-by":"publisher","unstructured":"Grossman, M., et al.: A pluggable framework for composable HPC scheduling libraries. In: 2017 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW), pp. 723\u2013732 (2017). https:\/\/doi.org\/10.1109\/IPDPSW.2017.13","DOI":"10.1109\/IPDPSW.2017.13"},{"key":"25_CR12","doi-asserted-by":"publisher","unstructured":"Guan, Q., et al.: F-sefi: a fine-grained soft error fault injection tool for profiling application vulnerability. In: 2014 IEEE 28th International Parallel and Distributed Processing Symposium, pp. 1245\u20131254 (2014). https:\/\/doi.org\/10.1109\/IPDPS.2014.128","DOI":"10.1109\/IPDPS.2014.128"},{"key":"25_CR13","doi-asserted-by":"publisher","unstructured":"Hayashi, A., et al.: Chapel-on-X: exploring tasking runtimes for PGAS languages. In: ESPM2 2017, pp. 5:1\u20135:8. ACM, New York (2017). https:\/\/doi.org\/10.1145\/3152041.3152086","DOI":"10.1145\/3152041.3152086"},{"key":"25_CR14","unstructured":"Heroux, M.A.: Toward Resilient Algorithms and Applications (2014). http:\/\/arxiv.org\/abs\/1402.3809"},{"issue":"6","key":"25_CR15","doi-asserted-by":"publisher","first-page":"518","DOI":"10.1109\/TC.1984.1676475","volume":"C-33","author":"Kuang-Hua Huang","year":"1984","unstructured":"Huang, K.H., Abraham, J.A.: Algorithm-based fault tolerance for matrix operations. IEEE Trans. Comput. C-33(6), 518\u2013528 (1984). https:\/\/doi.org\/10.1109\/TC.1984.1676475","journal-title":"IEEE Transactions on Computers"},{"key":"25_CR16","doi-asserted-by":"publisher","unstructured":"Jeannot, E.: Performance analysis and optimization of the tiled Cholesky factorization on NUMA machines. In: Proceedings of the 2012 Fifth International Symposium on Parallel Architectures, Algorithms and Programming, PAAP 2012, pp. 210\u2013217 (2012). https:\/\/doi.org\/10.1109\/PAAP.2012.38","DOI":"10.1109\/PAAP.2012.38"},{"key":"25_CR17","doi-asserted-by":"publisher","unstructured":"Kaiser, H., et al.: Parallex an advanced parallel execution model for scaling-impaired applications. In: 2009 International Conference on Parallel Processing Workshops, pp. 394\u2013401 (2009). https:\/\/doi.org\/10.1109\/ICPPW.2009.14","DOI":"10.1109\/ICPPW.2009.14"},{"key":"25_CR18","doi-asserted-by":"publisher","unstructured":"Li, D., et al.: 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 (2012). https:\/\/doi.org\/10.1109\/SC.2012.29","DOI":"10.1109\/SC.2012.29"},{"key":"25_CR19","doi-asserted-by":"publisher","unstructured":"Liu, Q., et al.: Compiler-directed lightweight checkpointing for fine-grained guaranteed soft error recovery. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, SC 2016, pp. 20:1\u201320:12 (2016). https:\/\/doi.org\/10.1109\/SC.2016.19","DOI":"10.1109\/SC.2016.19"},{"key":"25_CR20","doi-asserted-by":"publisher","unstructured":"Mattson, T.G., et al.: The open community runtime: a runtime system for extreme scale computing. In: 2016 IEEE High Performance Extreme Computing Conference (HPEC), pp. 1\u20137, September 2016. https:\/\/doi.org\/10.1109\/HPEC.2016.7761580","DOI":"10.1109\/HPEC.2016.7761580"},{"key":"25_CR21","doi-asserted-by":"publisher","unstructured":"Moody, A., et al.: Design, modeling, and evaluation of a scalable multi-level checkpointing system. In: Proceedings of the 2010 ACM\/IEEE International Conference for High Performance Computing, Networking, Storage and Analysis, SC 2010, pp. 1\u201311 (2010). https:\/\/doi.org\/10.1109\/SC.2010.18","DOI":"10.1109\/SC.2010.18"},{"issue":"10","key":"25_CR22","doi-asserted-by":"publisher","first-page":"972","DOI":"10.1109\/71.730527","volume":"9","author":"JS Plank","year":"1998","unstructured":"Plank, J.S., Li, K., Puening, M.A.: Diskless checkpointing. IEEE Trans. Parallel Distrib. Syst. 9(10), 972\u2013986 (1998). https:\/\/doi.org\/10.1109\/71.730527","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"25_CR23","doi-asserted-by":"publisher","unstructured":"Shantharam, M., et al.: Characterizing the impact of soft errors on iterative methods in scientific computing. In: Proceedings of the International Conference on Supercomputing, ICS 2011, pp. 152\u2013161 (2011). https:\/\/doi.org\/10.1145\/1995896.1995922","DOI":"10.1145\/1995896.1995922"},{"key":"25_CR24","doi-asserted-by":"publisher","unstructured":"Subasi, O., et al.: NanoCheckpoints: a task-based asynchronous dataflow framework for efficient and scalable checkpoint\/restart. In: 2015 23rd Euromicro International Conference on Parallel, Distributed, and Network-Based Processing, pp. 99\u2013102. https:\/\/doi.org\/10.1109\/PDP.2015.17","DOI":"10.1109\/PDP.2015.17"},{"key":"25_CR25","doi-asserted-by":"publisher","unstructured":"Subasi, O., et al.: Designing and modelling selective replication for fault-tolerant HPC applications. In: 2017 17th IEEE\/ACM International Symposium on Cluster, Cloud and Grid Computing (CCGRID), pp. 452\u2013457, May 2017. https:\/\/doi.org\/10.1109\/CCGRID.2017.40","DOI":"10.1109\/CCGRID.2017.40"}],"container-title":["Lecture Notes in Computer Science","Euro-Par 2019: Parallel Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-29400-7_25","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,13]],"date-time":"2023-08-13T00:04:31Z","timestamp":1691885071000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-29400-7_25"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030293994","9783030294007"],"references-count":25,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-29400-7_25","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":"13 August 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"Euro-Par","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Parallel Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"G\u00f6ttingen","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","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":"26 August 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 August 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"europar2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/europar.org\/","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":"142","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":"36","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":"25% - 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":"3,94","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":"4,27","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":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"double blind review in two cases","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}