{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,11]],"date-time":"2025-07-11T10:15:26Z","timestamp":1752228926899,"version":"3.40.5"},"publisher-location":"Cham","reference-count":29,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030410049"},{"type":"electronic","value":"9783030410056"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"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":[[2020]]},"DOI":"10.1007\/978-3-030-41005-6_11","type":"book-chapter","created":{"date-parts":[[2020,2,12]],"date-time":"2020-02-12T16:03:52Z","timestamp":1581523432000},"page":"153-169","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["ExaMPI: A Modern Design and Implementation to Accelerate Message Passing Interface Innovation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5252-6600","authenticated-orcid":false,"given":"Anthony","family":"Skjellum","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Martin","family":"R\u00fcfenacht","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1597-3369","authenticated-orcid":false,"given":"Nawrin","family":"Sultana","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8438-5144","authenticated-orcid":false,"given":"Derek","family":"Schafer","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9374-4433","authenticated-orcid":false,"given":"Ignacio","family":"Laguna","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1366-1655","authenticated-orcid":false,"given":"Kathryn","family":"Mohror","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,2,12]]},"reference":[{"key":"11_CR1","unstructured":"Cray MPI. \nhttps:\/\/pubs.cray.com\/content\/S-2529\/17.05\/xctm-series-programming-environment-user-guide-1705-s-2529\/mpt"},{"key":"11_CR2","unstructured":"IBM Spectrum MPI. \nhttps:\/\/tinyurl.com\/yy9cwm4p"},{"key":"11_CR3","unstructured":"MPI\/Pro. \nhttps:\/\/www.runtimecomputing.com\/products\/mpipro\/"},{"key":"11_CR4","unstructured":"Osu micro-benchmarks 5.6.2. \nhttp:\/\/mvapich.cse.ohio-state.edu\/benchmarks\/"},{"key":"11_CR5","unstructured":"Intel MPI library, August 2018. \nhttps:\/\/software.intel.com\/en-us\/mpi-library"},{"key":"11_CR6","unstructured":"Bangalore, P., Rabenseifner, R., Holmes, D., Jaeger, J., Mercier, G., Blaas-Schenner, C., Skjellum, A.: Exposition, clarification, and expansion of MPI semantic terms and conventions (2019). Under review"},{"key":"11_CR7","doi-asserted-by":"publisher","unstructured":"Barigou, Y., Venkatesan, V., Gabriel, E.: Auto-tuning non-blocking collective communication operations. In: 2015 IEEE International Parallel and Distributed Processing Symposium Workshop, pp. 1204\u20131213, May 2015. \nhttps:\/\/doi.org\/10.1109\/IPDPSW.2015.15","DOI":"10.1109\/IPDPSW.2015.15"},{"key":"11_CR8","doi-asserted-by":"publisher","unstructured":"Castillo, E., et al.: Optimizing computation-communication overlap in asynchronous task-based programs: poster. In: Proceedings of the 24th Symposium on Principles and Practice of Parallel Programming, PPoPP 2019, pp. 415\u2013416. ACM, New York (2019). \nhttps:\/\/doi.org\/10.1145\/3293883.3295720","DOI":"10.1145\/3293883.3295720"},{"key":"11_CR9","doi-asserted-by":"publisher","unstructured":"Denis, A., Trahay, F.: MPI overlap: benchmark and analysis. In: 2016 45th International Conference on Parallel Processing (ICPP), pp. 258\u2013267, August 2016. \nhttps:\/\/doi.org\/10.1109\/ICPP.2016.37","DOI":"10.1109\/ICPP.2016.37"},{"key":"11_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1007\/978-3-642-33518-1_9","volume-title":"Recent Advances in the Message Passing Interface","author":"S Didelot","year":"2012","unstructured":"Didelot, S., Carribault, P., P\u00e9rache, M., Jalby, W.: Improving MPI communication overlap with collaborative polling. In: Tr\u00e4ff, J.L., Benkner, S., Dongarra, J.J. (eds.) EuroMPI 2012. LNCS, vol. 7490, pp. 37\u201346. Springer, Heidelberg (2012). \nhttps:\/\/doi.org\/10.1007\/978-3-642-33518-1_9"},{"key":"11_CR11","unstructured":"Dimitrov, R.P.: Overlapping of communication and computation and early binding: fundamental mechanisms for improving parallel performance on clusters of workstations. Ph.D. thesis, Mississippi State, MS, USA (2001)"},{"key":"11_CR12","doi-asserted-by":"crossref","unstructured":"Graham, R.L., Shipman, G.M., Barrett, B.W., Castain, R.H., Bosilca, G., Lumsdaine, A.: Open MPI: a high-performance, heterogeneous MPI. In: Cluster 2006, pp. 1\u20139, September 2006","DOI":"10.1109\/CLUSTR.2006.311904"},{"key":"11_CR13","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"330","DOI":"10.1007\/978-3-030-20656-7_17","volume-title":"High Performance Computing","author":"RE Grant","year":"2019","unstructured":"Grant, R.E., Dosanjh, M.G.F., Levenhagen, M.J., Brightwell, R., Skjellum, A.: Finepoints: partitioned multithreaded MPI communication. In: Weiland, M., Juckeland, G., Trinitis, C., Sadayappan, P. (eds.) ISC High Performance 2019. LNCS, vol. 11501, pp. 330\u2013350. Springer, Cham (2019). \nhttps:\/\/doi.org\/10.1007\/978-3-030-20656-7_17"},{"key":"11_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1007\/3-540-45825-5_5","volume-title":"Recent Advances in Parallel Virtual Machine and Message Passing Interface","author":"W Gropp","year":"2002","unstructured":"Gropp, W.: MPICH2: a new start for MPI implementations. In: Kranzlm\u00fcller, D., Volkert, J., Kacsuk, P., Dongarra, J. (eds.) EuroPVM\/MPI 2002. LNCS, vol. 2474, pp. 7\u20137. Springer, Heidelberg (2002). \nhttps:\/\/doi.org\/10.1007\/3-540-45825-5_5"},{"key":"11_CR15","doi-asserted-by":"publisher","unstructured":"Guo, J., Yi, Q., Meng, J., Zhang, J., Balaji, P.: Compiler-assisted overlapping of communication and computation in MPI applications. In: 2016 IEEE International Conference on Cluster Computing (CLUSTER), pp. 60\u201369, September 2016. \nhttps:\/\/doi.org\/10.1109\/CLUSTER.2016.62","DOI":"10.1109\/CLUSTER.2016.62"},{"key":"11_CR16","unstructured":"Hager, G., Schubert, G., Wellein, G.: Prospects for truly asynchronous communication with pure MPI and hybrid MPI\/OpenMP on current supercomputing platforms (2011)"},{"key":"11_CR17","unstructured":"Hassani, A.: Toward a scalable, transactional, fault-tolerant message passing interface for petascale and exascale machines. Ph.D. thesis, UAB (2016)"},{"key":"11_CR18","doi-asserted-by":"publisher","unstructured":"Hoefler, T., Lumsdaine, A.: Message progression in parallel computing - to thread or not to thread? In: 2008 IEEE International Conference on Cluster Computing, pp. 213\u2013222, September 2008. \nhttps:\/\/doi.org\/10.1109\/CLUSTR.2008.4663774","DOI":"10.1109\/CLUSTR.2008.4663774"},{"key":"11_CR19","doi-asserted-by":"crossref","unstructured":"Holmes, D., et al.: MPI sessions: leveraging runtime infrastructure to increase scalability of applications at exascale. In: EuroMPI 2016, pp. 121\u2013129. ACM, New York (2016)","DOI":"10.1145\/2966884.2966915"},{"key":"11_CR20","first-page":"32","volume":"81","author":"DJ Holmes","year":"2019","unstructured":"Holmes, D.J., Morgan, B., Skjellum, A., Bangalore, P.V., Sridharan, S.: Planning for performance: Enhancing achievable performance for MPI through persistent collective operations. PARCOMP 81, 32\u201357 (2019)","journal-title":"PARCOMP"},{"key":"11_CR21","unstructured":"ISO: ISO\/IEC 14882:2017 Information technology \u2013 Programming languages \u2013 C++. Fifth edn., December 2017. \nhttps:\/\/tinyurl.com\/yct5hxcs"},{"key":"11_CR22","doi-asserted-by":"publisher","unstructured":"Liu, J., et al.: Performance comparison of MPI implementations over Infiniband, Myrinet and Quadrics. In: Proceedings of the 2003 ACM\/IEEE Conference on Supercomputing, SC 2003, pp. 58\u201358, November 2003. \nhttps:\/\/doi.org\/10.1109\/SC.2003.10007","DOI":"10.1109\/SC.2003.10007"},{"key":"11_CR23","doi-asserted-by":"crossref","unstructured":"Laguna, I., Mohror, K., Sultana, N., R\u00fcfenacht, M., Marshall, R., Skjellum, A.: A large-scale study of MPI usage in open-source HPC applications. In: Proceedings of the SC 2019, November 2019 (2019, in press). \nhttps:\/\/github.com\/LLNL\/MPI-Usage","DOI":"10.1145\/3295500.3356176"},{"key":"11_CR24","doi-asserted-by":"publisher","unstructured":"Lu, H., Seo, S., Balaji, P.: MPI+ULT: overlapping communication and computation with user-level threads. In: 2015 IEEE 17th International Conference on High Performance Computing and Communications, 2015 IEEE 7th International Symposium on Cyberspace Safety and Security, and 2015 IEEE 12th International Conference on Embedded Software and Systems, pp. 444\u2013454, August 2015. \nhttps:\/\/doi.org\/10.1109\/HPCC-CSS-ICESS.2015.82","DOI":"10.1109\/HPCC-CSS-ICESS.2015.82"},{"key":"11_CR25","unstructured":"Panda, D.K., Tomko, K., Schulz, K., Majumdar, A.: The MVAPICH project: evolution and sustainability of an open source production quality MPI library for HPC. In: WSPPE (2013)"},{"key":"11_CR26","doi-asserted-by":"publisher","unstructured":"Skjellum, A., et al.: Object-oriented analysis and design of the message passing interface. Concurrency Comput.: Practice Exp. 13(4), 245\u2013292 (2001). \nhttps:\/\/doi.org\/10.1002\/cpe.556","DOI":"10.1002\/cpe.556"},{"key":"11_CR27","doi-asserted-by":"publisher","unstructured":"Sridharan, S., Dinan, J., Kalamkar, D.D.: Enabling efficient multithreaded MPI communication through a library-based implementation of MPI endpoints. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, SC 2014, pp. 487\u2013498. IEEE Press, Piscataway (2014). \nhttps:\/\/doi.org\/10.1109\/SC.2014.45","DOI":"10.1109\/SC.2014.45"},{"key":"11_CR28","first-page":"1","volume":"84","author":"N Sultana","year":"2019","unstructured":"Sultana, N., R\u00fcfenacht, M., Skjellum, A., Laguna, I., Mohror, K.: Failure recovery for bulk synchronous applications with MPI stages. PARCOMP 84, 1\u201314 (2019)","journal-title":"PARCOMP"},{"key":"11_CR29","unstructured":"Wittmann, M., Hager, G., Zeiser, T., Wellein, G.: Asynchronous MPI for the masses. arXiv preprint \narXiv:1302.4280\n\n (2013)"}],"container-title":["Communications in Computer and Information Science","High Performance Computing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-41005-6_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,2,13]],"date-time":"2020-02-13T01:46:27Z","timestamp":1581558387000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-41005-6_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030410049","9783030410056"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-41005-6_11","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"12 February 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CARLA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Latin American High Performance Computing Conference","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Turrialba","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Costa Rica","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":"25 September 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 September 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"carla2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/carla2019.ccarla.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":"OCS","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"62","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":"32","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":"52% - 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","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":"3","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)"}}]}}