{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T00:59:44Z","timestamp":1740099584545,"version":"3.37.3"},"publisher-location":"Cham","reference-count":39,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030346263"},{"type":"electronic","value":"9783030346270"}],"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\/978-3-030-34627-0_10","type":"book-chapter","created":{"date-parts":[[2019,11,12]],"date-time":"2019-11-12T09:02:55Z","timestamp":1573549375000},"page":"120-137","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["MATE, a Unified Model for Communication-Tolerant Scientific Applications"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3628-3992","authenticated-orcid":false,"given":"Sergio M.","family":"Martin","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5479-8199","authenticated-orcid":false,"given":"Scott B.","family":"Baden","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,11,13]]},"reference":[{"key":"10_CR1","unstructured":"https:\/\/www.mpi-forum.org\/"},{"key":"10_CR2","unstructured":"https:\/\/www.openmp.org\/"},{"key":"10_CR3","unstructured":"http:\/\/www.nersc.gov\/users\/computational-systems\/cori\/configuration\/"},{"key":"10_CR4","unstructured":"http:\/\/uk-mac.github.io\/CloverLeaf3D\/"},{"key":"10_CR5","unstructured":"Cray MPI. \nhttps:\/\/pubs.cray.com\/"},{"key":"10_CR6","unstructured":"Intel MPI library. \nhttps:\/\/software.intel.com\/en-us\/intel-mpi-library"},{"key":"10_CR7","unstructured":"MPICH library. \nhttp:\/\/www.mpich.org\/"},{"key":"10_CR8","unstructured":"MVAPICH library. \nhttp:\/\/mvapich.cse.ohio-state.edu\/"},{"key":"10_CR9","unstructured":"Open MPI library. \nhttps:\/\/www.open-mpi.org\/"},{"issue":"3","key":"10_CR10","doi-asserted-by":"publisher","first-page":"300","DOI":"10.1109\/12.48862","volume":"39","author":"K Arvind","year":"1990","unstructured":"Arvind, K., Nikhil, R.S.: Executing a program on the MIT tagged-token dataflow architecture. IEEE Trans. Comput. 39(3), 300\u2013318 (1990). \nhttps:\/\/doi.org\/10.1109\/12.48862","journal-title":"IEEE Trans. Comput."},{"issue":"7","key":"10_CR11","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1109\/MC.1984.1659186","volume":"17","author":"RG Babb","year":"1984","unstructured":"Babb, R.G.: Parallel processing with large-grain data flow technique. Computer 17(7), 55\u201361 (1984)","journal-title":"Computer"},{"key":"10_CR12","doi-asserted-by":"publisher","unstructured":"Bachan, J., et al.: The UPC++ PGAS library for exascale computing: extended abstract. In: PAW17: Second Annual PGAS Applications Workshop, p. 4. ACM, New York, 12\u201317 November 2017. \nhttps:\/\/doi.org\/10.1145\/3144779.3169108","DOI":"10.1145\/3144779.3169108"},{"key":"10_CR13","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1017\/S0962492914000038","volume":"23","author":"G Ballard","year":"2014","unstructured":"Ballard, G., Carson, E., Demmel, J., Hoemmen, M., Knight, N., Schwartz, O.: Communication lower bounds and optimal algorithms for numerical linear algebra. Acta Numerica 23, 1\u2013155 (2014)","journal-title":"Acta Numerica"},{"key":"10_CR14","doi-asserted-by":"publisher","unstructured":"Barrett, R.F., Stark, D.T., Vaughan, C.T., Grant, R.E., Olivier, S.L., Pedretti, K.T.: Toward an evolutionary task parallel integrated MPI + X programming model. In: Proceedings of the Sixth International Workshop on Programming Models and Applications for Multicores and Manycores, PMAM 2015, pp. 30\u201339. ACM, New York (2015). \nhttps:\/\/doi.org\/10.1145\/2712386.2712388","DOI":"10.1145\/2712386.2712388"},{"key":"10_CR15","unstructured":"Cannon, L.E.: A Cellular computer to implement the Kalman filter algorithm. Ph.D. thesis, Bozeman, MT, USA (1969). aAI7010025"},{"key":"10_CR16","doi-asserted-by":"publisher","unstructured":"Chaimov, N., Ibrahim, K.Z., Williams, S., Iancu, C.: Exploiting communication concurrency on high performance computing systems. In: Proceedings of the Sixth International Workshop on Programming Models and Applications for Multicores and Manycores, PMAM 2015, pp. 132\u2013143. ACM, New York (2015). \nhttps:\/\/doi.org\/10.1145\/2712386.2712394","DOI":"10.1145\/2712386.2712394"},{"key":"10_CR17","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1007\/11557265_8","volume-title":"Recent Advances in Parallel Virtual Machine and Message Passing Interface","author":"A Debudaj-Grabysz","year":"2005","unstructured":"Debudaj-Grabysz, A., Rabenseifner, R.: Nesting OpenMP in MPI to implement a hybrid communication method of parallel simulated annealing on a cluster of SMP nodes. In: Di Martino, B., Kranzlm\u00fcller, D., Dongarra, J. (eds.) EuroPVM\/MPI 2005. LNCS, vol. 3666, pp. 18\u201327. Springer, Heidelberg (2005). \nhttps:\/\/doi.org\/10.1007\/11557265_8"},{"issue":"11","key":"10_CR18","doi-asserted-by":"publisher","first-page":"48","DOI":"10.1109\/MC.1980.1653418","volume":"13","author":"J Dennis","year":"1980","unstructured":"Dennis, J.: Data flow supercomputers. IEEE Comput. 13(11), 48\u201356 (1980)","journal-title":"IEEE Comput."},{"key":"10_CR19","doi-asserted-by":"publisher","first-page":"1121","DOI":"10.1007\/s00607-013-0324-2","volume":"95","author":"T Hoefler","year":"2013","unstructured":"Hoefler, T., et al.: MPI + MPI: a new hybrid approach to parallel programming with MPI plus shared memory. Computing 95, 1121\u20131136 (2013). \nhttps:\/\/doi.org\/10.1007\/s00607-013-0324-2","journal-title":"Computing"},{"key":"10_CR20","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"306","DOI":"10.1007\/978-3-540-24644-2_20","volume-title":"Languages and Compilers for Parallel Computing","author":"C Huang","year":"2004","unstructured":"Huang, C., Lawlor, O., Kal\u00e9, L.V.: Adaptive MPI. In: Rauchwerger, L. (ed.) LCPC 2003. LNCS, vol. 2958, pp. 306\u2013322. Springer, Heidelberg (2004). \nhttps:\/\/doi.org\/10.1007\/978-3-540-24644-2_20"},{"key":"10_CR21","doi-asserted-by":"publisher","unstructured":"Iancu, C., Hofmeyr, S., Blagojevi\u0107, F., Zheng, Y.: Oversubscription on multicore processors. In: 2010 IEEE International Symposium on Parallel Distributed Processing (IPDPS), pp. 1\u201311 (April 2010). \nhttps:\/\/doi.org\/10.1109\/IPDPS.2010.5470434","DOI":"10.1109\/IPDPS.2010.5470434"},{"key":"10_CR22","doi-asserted-by":"publisher","first-page":"215","DOI":"10.1142\/S0129626400000214","volume":"10","author":"D Quinlan","year":"2000","unstructured":"Quinlan, D.: ROSE: compiler support for object-oriented frameworks. Parallel Process. Lett. 10, 215\u2013226 (2000)","journal-title":"Parallel Process. Lett."},{"key":"10_CR23","unstructured":"Kal\u00e9, L.V.: The virtualization approach to parallel programming: runtime optimizations and the state of the art. In: Los Alamos Computer Science Institute Symposium-LACSI (2002)"},{"key":"10_CR24","doi-asserted-by":"publisher","unstructured":"Kale, L.V., Krishnan, S.: CHARM++: a portable concurrent object oriented system based on C++. In: Proceedings of the Eighth Annual Conference on Object-oriented Programming Systems, Languages, and Applications, OOPSLA 1993, pp. 91\u2013108. ACM, New York (1993). \nhttps:\/\/doi.org\/10.1145\/165854.165874","DOI":"10.1145\/165854.165874"},{"key":"10_CR25","doi-asserted-by":"publisher","unstructured":"Kamal, H., Wagner, A.: FG-MPI: fine-grain MPI for multicore and clusters. In: 2010 IEEE International Symposium on Parallel Distributed Processing, Workshops and Phd Forum (IPDPSW), pp. 1\u20138, April 2010. \nhttps:\/\/doi.org\/10.1109\/IPDPSW.2010.5470773","DOI":"10.1109\/IPDPSW.2010.5470773"},{"key":"10_CR26","doi-asserted-by":"publisher","unstructured":"Krishnamurthy, A., et al.: Parallel programming in split-C. In: Proceedings of the 1993 ACM\/IEEE Conference on Supercomputing, Supercomputing 1993, pp. 262\u2013273. ACM, New York (1993). \nhttps:\/\/doi.org\/10.1145\/169627.169724","DOI":"10.1145\/169627.169724"},{"key":"10_CR27","doi-asserted-by":"publisher","unstructured":"Lavrijsen, W., Iancu, C.: Application level reordering of remote direct memory access operations. In: 2017 IEEE International Parallel and Distributed Processing Symposium (IPDPS), pp. 988\u2013997, May 2017. \nhttps:\/\/doi.org\/10.1109\/IPDPS.2017.98","DOI":"10.1109\/IPDPS.2017.98"},{"key":"10_CR28","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":"10_CR29","doi-asserted-by":"publisher","unstructured":"Marjanovi\u0107, V., Labarta, J., Ayguad\u00e9, E., Valero, M.: Overlapping communication and computation by using a hybrid MPI\/SMPSS approach. In: Proceedings of the 24th ACM International Conference on Supercomputing, ICS 2010, pp. 5\u201316. ACM, New York (2010). \nhttps:\/\/doi.org\/10.1145\/1810085.1810091","DOI":"10.1145\/1810085.1810091"},{"key":"10_CR30","doi-asserted-by":"publisher","unstructured":"Martin, S.M., Berger, M.J., Baden, S.B.: Toucan - a translator for communication tolerant MPI applications. In: 2017 IEEE International Parallel and Distributed Processing Symposium (IPDPS), pp. 998\u20131007, May 2017. \nhttps:\/\/doi.org\/10.1109\/IPDPS.2017.44","DOI":"10.1109\/IPDPS.2017.44"},{"key":"10_CR31","unstructured":"NERSC: National Energy Research Scientific Computing Center. \nhttp:\/\/www.nersc.gov"},{"key":"10_CR32","doi-asserted-by":"publisher","unstructured":"Nguyen, T., Cicotti, P., Bylaska, E., Quinlan, D., Baden, S.B.: Bamboo - translating MPI applications to a latency-tolerant, data-driven form. In: 2012 International Conference for High Performance Computing, Networking, Storage and Analysis (SC), pp. 1\u201311, November 2012. \nhttps:\/\/doi.org\/10.1109\/SC.2012.23","DOI":"10.1109\/SC.2012.23"},{"key":"10_CR33","unstructured":"OpenMP, ARB: OpenMP 4.0 specification (2013)"},{"key":"10_CR34","doi-asserted-by":"publisher","unstructured":"Perez, J.M., Badia, R.M., Labarta, J.: A dependency-aware task-based programming environment for multi-core architectures. In: 2008 IEEE International Conference on Cluster Computing, pp. 142\u2013151, September 2008. \nhttps:\/\/doi.org\/10.1109\/CLUSTR.2008.4663765","DOI":"10.1109\/CLUSTR.2008.4663765"},{"key":"10_CR35","doi-asserted-by":"publisher","unstructured":"Tang, H., Yang, T.: Optimizing threaded MPI execution on SMP clusters. In: Proceedings of the 15th International Conference on Supercomputing, ICS 2001, pp. 381\u2013392. ACM, New York (2001). \nhttps:\/\/doi.org\/10.1145\/377792.377895","DOI":"10.1145\/377792.377895"},{"key":"10_CR36","doi-asserted-by":"publisher","first-page":"157","DOI":"10.1007\/978-3-642-11261-4_11","volume-title":"Tools for High Performance Computing 2009","author":"D Terpstra","year":"2010","unstructured":"Terpstra, D., Jagode, H., You, H., Dongarra, J.: Collecting performance data with PAPI-C. In: M\u00fcller, M.S., Resch, M.M., Schulz, A., Nagel, W.E. (eds.) Tools for High Performance Computing 2009, pp. 157\u2013173. Springer, Heidelberg (2010). \nhttps:\/\/doi.org\/10.1007\/978-3-642-11261-4_11"},{"issue":"1","key":"10_CR37","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1147\/rd.111.0025","volume":"11","author":"RM Tomasulo","year":"1967","unstructured":"Tomasulo, R.M.: An efficient algorithm for exploiting multiple arithmetic units. IBM J. Res. Dev. 11(1), 25\u201333 (1967). \nhttps:\/\/doi.org\/10.1147\/rd.111.0025","journal-title":"IBM J. Res. Dev."},{"issue":"8","key":"10_CR38","doi-asserted-by":"publisher","first-page":"103","DOI":"10.1145\/79173.79181","volume":"33","author":"LG Valiant","year":"1990","unstructured":"Valiant, L.G.: A bridging model for parallel computation. Commun. ACM 33(8), 103\u2013111 (1990). \nhttps:\/\/doi.org\/10.1145\/79173.79181","journal-title":"Commun. ACM"},{"issue":"2","key":"10_CR39","doi-asserted-by":"publisher","first-page":"B179","DOI":"10.1137\/110820105","volume":"34","author":"Q Zhang","year":"2012","unstructured":"Zhang, Q., Johansen, H., Colella, P.: A fourth-order accurate finite-volume method with structured adaptive mesh refinement for solving the advection-diffusion equation. SIAM J. Sci. Comput. 34(2), B179\u2013B201 (2012). \nhttps:\/\/doi.org\/10.1137\/110820105","journal-title":"SIAM J. Sci. Comput."}],"container-title":["Lecture Notes in Computer Science","Languages and Compilers for Parallel Computing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-34627-0_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,11,12]],"date-time":"2019-11-12T09:04:27Z","timestamp":1573549467000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-34627-0_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030346263","9783030346270"],"references-count":39,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-34627-0_10","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 November 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"LCPC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Workshop on Languages and Compilers for Parallel Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Salt Lake City, UT","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"USA","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 October 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 October 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"lcpc2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.lcpcworkshop.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Confy","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"26","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":"14","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":"54% - 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":"2","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":"2","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)"}}]}}