{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T19:26:41Z","timestamp":1777058801985,"version":"3.51.4"},"publisher-location":"Cham","reference-count":22,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031396977","type":"print"},{"value":"9783031396984","type":"electronic"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-39698-4_4","type":"book-chapter","created":{"date-parts":[[2023,8,23]],"date-time":"2023-08-23T06:02:40Z","timestamp":1692770560000},"page":"47-61","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Fault-Aware Group-Collective Communication Creation and\u00a0Repair in\u00a0MPI"],"prefix":"10.1007","author":[{"given":"Roberto","family":"Rocco","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gianluca","family":"Palermo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,8,24]]},"reference":[{"issue":"3","key":"4_CR1","doi-asserted-by":"publisher","first-page":"244","DOI":"10.1177\/1094342013488238","volume":"27","author":"W Bland","year":"2013","unstructured":"Bland, W., Bouteiller, A., et al.: Post-failure recovery of MPI communication capability: design and rationale. Int. J. High Perform. Comput. Appl. 27(3), 244\u2013254 (2013)","journal-title":"Int. J. High Perform. Comput. Appl."},{"key":"4_CR2","doi-asserted-by":"crossref","unstructured":"Bouteiller, A., Bosilca, G.: Implicit actions and non-blocking failure recovery with MPI. arXiv preprint arXiv:2212.08755 (2022)","DOI":"10.1109\/FTXS56515.2022.00009"},{"issue":"3","key":"4_CR3","doi-asserted-by":"publisher","first-page":"319","DOI":"10.1177\/1094342006067469","volume":"20","author":"A Bouteiller","year":"2006","unstructured":"Bouteiller, A., Herault, T., et al.: Mpich-v project: a multiprotocol automatic fault-tolerant MPI. Int. J. High Perform. Comput. Appl. 20(3), 319\u2013333 (2006)","journal-title":"Int. J. High Perform. Comput. Appl."},{"key":"4_CR4","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/978-3-0348-8534-8_21","volume-title":"Programming environments for massively parallel distributed systems","author":"L Clarke","year":"1994","unstructured":"Clarke, L., Glendinning, I., et al.: The MPI message passing interface standard. In: Decker, K.M., Rehmann, R.M. (eds.) Programming environments for massively parallel distributed systems, pp. 213\u2013218. Springer, Cham (1994). https:\/\/doi.org\/10.1007\/978-3-0348-8534-8_21"},{"key":"4_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"282","DOI":"10.1007\/978-3-642-24449-0_32","volume-title":"Recent Advances in the Message Passing Interface","author":"J Dinan","year":"2011","unstructured":"Dinan, J., et al.: Noncollective communicator creation in MPI. In: Cotronis, Y., Danalis, A., Nikolopoulos, D.S., Dongarra, J. (eds.) EuroMPI 2011. LNCS, vol. 6960, pp. 282\u2013291. Springer, Heidelberg (2011). https:\/\/doi.org\/10.1007\/978-3-642-24449-0_32"},{"key":"4_CR6","unstructured":"Dixit, H.D., Pendharkar, S., et al.: Silent data corruptions at scale. arXiv preprint arXiv:2102.11245 (2021)"},{"issue":"3","key":"4_CR7","doi-asserted-by":"publisher","first-page":"1302","DOI":"10.1007\/s11227-013-0884-0","volume":"65","author":"IP Egwutuoha","year":"2013","unstructured":"Egwutuoha, I.P., Levy, D., et al.: A survey of fault tolerance mechanisms and checkpoint\/restart implementations for high performance computing systems. J. Supercomput. 65(3), 1302\u20131326 (2013)","journal-title":"J. Supercomput."},{"key":"4_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"346","DOI":"10.1007\/3-540-45255-9_47","volume-title":"Recent Advances in Parallel Virtual Machine and Message Passing Interface","author":"GE Fagg","year":"2000","unstructured":"Fagg, G.E., Dongarra, J.J.: FT-MPI: fault tolerant MPI, supporting dynamic applications in a dynamic world. In: Dongarra, J., Kacsuk, P., Podhorszki, N. (eds.) EuroPVM\/MPI 2000. LNCS, vol. 1908, pp. 346\u2013353. Springer, Heidelberg (2000). https:\/\/doi.org\/10.1007\/3-540-45255-9_47"},{"key":"4_CR9","unstructured":"Ferreira, K., Riesen, R., et al.: rMPI: increasing fault resiliency in a message-passing environment. Sandia National Laboratories, Albuquerque, NM, Technical report SAND2011-2488 (2011)"},{"key":"4_CR10","doi-asserted-by":"crossref","unstructured":"Gamell, M., Katz, D.S., et al.: Exploring automatic, online failure recovery for scientific applications at extreme scales. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, SC 2014. pp. 895\u2013906. IEEE (2014)","DOI":"10.1109\/SC.2014.78"},{"key":"4_CR11","doi-asserted-by":"crossref","unstructured":"Hassani, A., Skjellum, A., et al.: 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. IEEE (2014)","DOI":"10.1109\/DSN.2014.78"},{"key":"4_CR12","doi-asserted-by":"crossref","unstructured":"Hochschild, P.H., Turner, P., et al.: Cores that don\u2019t count. In: Proceedings of the Workshop on Hot Topics in Operating Systems, pp. 9\u201316 (2021)","DOI":"10.1145\/3458336.3465297"},{"key":"4_CR13","doi-asserted-by":"crossref","unstructured":"Holmes, D., Mohror, K., et al.: MPI sessions: leveraging runtime infrastructure to increase scalability of applications at exascale. In: Proceedings of the 23rd European MPI Users\u2019 Group Meeting, pp. 121\u2013129 (2016)","DOI":"10.1145\/2966884.2966915"},{"issue":"3","key":"4_CR14","doi-asserted-by":"publisher","first-page":"305","DOI":"10.1177\/1094342015623623","volume":"30","author":"I Laguna","year":"2016","unstructured":"Laguna, I., Richards, D.F., et al.: Evaluating and extending user-level fault tolerance in MPI applications. Int. J. High Perform. Comput. Appl. 30(3), 305\u2013319 (2016)","journal-title":"Int. J. High Perform. Comput. Appl."},{"key":"4_CR15","doi-asserted-by":"crossref","unstructured":"Lamport, L., Melliar-Smith, P.M.: Byzantine clock synchronization. In: Proceedings of the Third Annual ACM Symposium on Principles of Distributed Computing, pp. 68\u201374 (1984)","DOI":"10.1145\/800222.806737"},{"issue":"1","key":"4_CR16","doi-asserted-by":"publisher","first-page":"100","DOI":"10.1007\/s11227-016-1629-7","volume":"73","author":"N Losada","year":"2017","unstructured":"Losada, N., Cores, I., et al.: Resilient MPI applications using an application-level checkpointing framework and ULFM. J. Supercomput, 73(1), 100\u2013113 (2017)","journal-title":"J. Supercomput,"},{"issue":"14","key":"4_CR17","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.5826","volume":"33","author":"A Margolin","year":"2021","unstructured":"Margolin, A., Barak, A.: Tree-based fault-tolerant collective operations for MPI. Concurr. Comput.: Pract. Exp. 33(14), e5826 (2021)","journal-title":"Concurr. Comput.: Pract. Exp."},{"key":"4_CR18","first-page":"1","volume":"78","author":"R Rocco","year":"2021","unstructured":"Rocco, R., Gadioli, D., et al.: Legio: fault resiliency for embarrassingly parallel MPI applications. J. Supercomput. 78, 1\u201321 (2021)","journal-title":"J. Supercomput."},{"issue":"3","key":"4_CR19","doi-asserted-by":"publisher","first-page":"501","DOI":"10.1109\/TPDS.2018.2866794","volume":"30","author":"F Shahzad","year":"2018","unstructured":"Shahzad, F., Thies, J., et al.: Craft: a library for easier application-level checkpoint\/restart and automatic fault tolerance. IEEE Trans. Parallel Distrib. Syst. 30(3), 501\u2013514 (2018)","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"4_CR20","doi-asserted-by":"crossref","unstructured":"Sultana, N., Skjellum, A., et al.: MPI stages: checkpointing MPI state for bulk synchronous applications. In: Proceedings of the 25th European MPI Users\u2019 Group Meeting, pp. 1\u201311 (2018)","DOI":"10.1145\/3236367.3236385"},{"key":"4_CR21","doi-asserted-by":"crossref","unstructured":"Suo, G., Lu, Y., et al.: NR-MPI: a non-stop and fault resilient MPI. In: 2013 International Conference on Parallel and Distributed Systems, pp. 190\u2013199. IEEE (2013)","DOI":"10.1109\/ICPADS.2013.37"},{"key":"4_CR22","doi-asserted-by":"crossref","unstructured":"Teranishi, K., Heroux, M.A.: Toward local failure local recovery resilience model using MPI-ULFM. In: Proceedings of the 21st European MPI users\u2019 group meeting, pp. 51\u201356 (2014)","DOI":"10.1145\/2642769.2642774"}],"container-title":["Lecture Notes in Computer Science","Euro-Par 2023: Parallel Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-39698-4_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,23]],"date-time":"2023-08-23T06:03:58Z","timestamp":1692770638000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-39698-4_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031396977","9783031396984"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-39698-4_4","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"24 August 2023","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":"Limassol","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Cyprus","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 August 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 September 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"europar2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/2023.euro-par.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":"164","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":"49","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":"30% - 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":"3.98","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","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)"}}]}}