{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,10]],"date-time":"2026-01-10T08:21:40Z","timestamp":1768033300000,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":35,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,9,11]],"date-time":"2023-09-11T00:00:00Z","timestamp":1694390400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"DOE","award":["DE-AC05-00OR2272"],"award-info":[{"award-number":["DE-AC05-00OR2272"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,9,11]]},"DOI":"10.1145\/3615318.3615327","type":"proceedings-article","created":{"date-parts":[[2023,9,21]],"date-time":"2023-09-21T21:09:55Z","timestamp":1695330595000},"page":"1-11","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Optimizing Communication in 2D Grid-Based MPI Applications at Exascale"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8941-870X","authenticated-orcid":false,"given":"Hao","family":"Lu","sequence":"first","affiliation":[{"name":"Oak Ridge National Laboratory, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9432-5855","authenticated-orcid":false,"given":"Piyush","family":"Sao","sequence":"additional","affiliation":[{"name":"Oak Ridge National Laboratory, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1512-5255","authenticated-orcid":false,"given":"Michael","family":"Matheson","sequence":"additional","affiliation":[{"name":"Oak Ridge National Laboratory, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5852-4806","authenticated-orcid":false,"given":"Ramakrishnan","family":"Kannan","sequence":"additional","affiliation":[{"name":"Oak Ridge National Laboratory, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0099-1559","authenticated-orcid":false,"given":"Feiyi","family":"Wang","sequence":"additional","affiliation":[{"name":"Oak Ridge National Laboratory, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6687-3435","authenticated-orcid":false,"given":"Thomas","family":"Potok","sequence":"additional","affiliation":[{"name":"Oak Ridge National Laboratory, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,9,21]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Numerical linear algebra on emerging architectures: The PLASMA and MAGMA projects. 180, 1","author":"Agullo Emmanuel","year":"2009","unstructured":"Emmanuel Agullo, Jim Demmel, Jack Dongarra, Bilel Hadri, Jakub Kurzak, Julien Langou, Hatem Ltaief, Piotr Luszczek, and Stanimire Tomov. 2009. Numerical linear algebra on emerging architectures: The PLASMA and MAGMA projects. 180, 1 (2009), 012037."},{"key":"e_1_3_2_1_2_1","volume-title":"Accessed","author":"AMD.","year":"2021","unstructured":"AMD. [n.d.]. AMD ROCm Platform Portal. Accessed Oct. 21, 2021. https:\/\/rocmdocs.amd.com\/en\/latest\/"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC43674.2020.9286214"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1177\/1094342011403516"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1177\/1094342007078442"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/FMPC.1992.234898"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3322125"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/2716320"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2014.46"},{"key":"e_1_3_2_1_10_1","volume-title":"Proceedings of the 2006 ACM\/IEEE conference on Supercomputing. 27\u2013es.","author":"El-Ghazawi Tarek","year":"2006","unstructured":"Tarek El-Ghazawi and Lauren Smith. 2006. UPC: unified parallel C. In Proceedings of the 2006 ACM\/IEEE conference on Supercomputing. 27\u2013es."},{"key":"e_1_3_2_1_11_1","volume-title":"Fineman and Eric Robinson","author":"T.","year":"2011","unstructured":"Jeremy\u00a0T. Fineman and Eric Robinson. 2011. Fundamental graph algorithms. In Graph Algorithms in the Language of Linear Algebra, Jeremy Kepner and John Gilbert (Eds.). Society of Industrial and Applied Mathematics, Philadelphia, PA, USA, Chapter\u00a05, 45\u201358."},{"key":"e_1_3_2_1_12_1","volume-title":"Fineman and Eric Robinson","author":"T.","year":"2011","unstructured":"Jeremy\u00a0T. Fineman and Eric Robinson. 2011. Fundamental graph algorithms. In Graph Algorithms in the Language of Linear Algebra, Jeremy Kepner and John Gilbert (Eds.). Society of Industrial and Applied Mathematics, Philadelphia, PA, USA, Chapter\u00a05, 45\u201358."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1137\/1032002"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"crossref","unstructured":"Mark Gates Jakub Kurzak Ali Charara Asim YarKhan and Jack Dongarra. 2019. SLATE: Design of a modern distributed and accelerated linear algebra library. In SC19:Proceedings of the International Conference for High Performance Computing Networking Storage and Analysis. 1\u201318.","DOI":"10.1145\/3295500.3356223"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1098\/rspa.2020.0110"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2018.00050"},{"key":"e_1_3_2_1_17_1","volume-title":"Accuracy and Stability of Numerical Algorithms","author":"Higham J.","unstructured":"Nicholas\u00a0J. Higham. 2002. Accuracy and Stability of Numerical Algorithms (2nd ed.). Society for Industrial and Applied Mathematics, USA.","edition":"2"},{"key":"e_1_3_2_1_18_1","volume-title":"HPL-AI Mixed-Precision Benchmark. Accessed","author":"ICL.","year":"2021","unstructured":"ICL. [n.d.]. HPL-AI Mixed-Precision Benchmark. Accessed Aug. 1, 2021. https:\/\/hpl-ai.org\/"},{"key":"e_1_3_2_1_19_1","volume-title":"Proc Int Conf Parallel Process","author":"Jenq Jing\u00a0Fu","year":"1987","unstructured":"Jing\u00a0Fu Jenq and Sartaj Sahni. 1987. ALL PAIRS SHORTEST PATHS ON A HYPERCUBE MULTIPROCESSOR.. In Proc Int Conf Parallel Process 1987. Pennsylvania State Univ Press, 713\u2013716."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00010"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.5555\/3571885.3571892"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ScalA51936.2020.00014"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1016\/0743-7315(91)90083-L"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CIT.2010.212"},{"key":"e_1_3_2_1_26_1","volume-title":"A new scalable parallel algorithm for Fock matrix construction. In 2014 IEEE 28th international parallel and distributed processing symposium","author":"Liu Xing","unstructured":"Xing Liu, Aftab Patel, and Edmond Chow. 2014. A new scalable parallel algorithm for Fock matrix construction. In 2014 IEEE 28th international parallel and distributed processing symposium. IEEE, 902\u2013914."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC41404.2022.00083"},{"key":"e_1_3_2_1_28_1","volume-title":"ACM Sigplan Fortran Forum, Vol.\u00a017. ACM New York","author":"Numrich W","unstructured":"Robert\u00a0W Numrich and John Reid. 1998. Co-Array Fortran for parallel programming. In ACM Sigplan Fortran Forum, Vol.\u00a017. ACM New York, NY, USA, 1\u201331."},{"key":"e_1_3_2_1_29_1","volume-title":"Accessed","author":"NVIDIA.","year":"2021","unstructured":"NVIDIA. [n.d.]. NVIDIA CUDA Toolkit Documentation. Accessed Apr. 21, 2021. https:\/\/docs.nvidia.com\/cuda\/index.html"},{"key":"e_1_3_2_1_30_1","volume-title":"Accessed","author":"RIKEN-RCCS.","year":"2021","unstructured":"RIKEN-RCCS. [n.d.]. HPL-AI implementation for Fugaku. Accessed Apr. 21, 2021. https:\/\/github.com\/RIKEN-RCCS\/hpl-ai"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3332466.3374533"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3431379.3460651"},{"key":"e_1_3_2_1_33_1","volume-title":"Numerical Algorithms for Modern Parallel Computer Architectures","author":"Schreiber Robert","unstructured":"Robert Schreiber. 1988. Block Algorithms for Parallel Machines. In Numerical Algorithms for Modern Parallel Computer Architectures, Martin Schultz (Ed.). Springer US, New York, NY, 197\u2013207."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.21236\/ADA580350"},{"key":"e_1_3_2_1_35_1","volume-title":"Introduction to Linear Algebra (5 ed.)","author":"Strang Gilbert","unstructured":"Gilbert Strang. 2016. Introduction to Linear Algebra (5 ed.). Wellesley-Cambridge Press, Wellesley, MA."},{"key":"e_1_3_2_1_36_1","volume-title":"Rounding Errors in Algebraic Processes","author":"Wilkinson H.","unstructured":"James\u00a0H. Wilkinson. 1994. Rounding Errors in Algebraic Processes. Dover Publications, Inc., USA."}],"event":{"name":"EUROMPI '23: 30th European MPI Users' Group Meeting","location":"Bristol United Kingdom","acronym":"EUROMPI '23"},"container-title":["Proceedings of the 30th European MPI Users' Group Meeting"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3615318.3615327","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3615318.3615327","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3615318.3615327","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:36:53Z","timestamp":1750178213000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3615318.3615327"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9,11]]},"references-count":35,"alternative-id":["10.1145\/3615318.3615327","10.1145\/3615318"],"URL":"https:\/\/doi.org\/10.1145\/3615318.3615327","relation":{},"subject":[],"published":{"date-parts":[[2023,9,11]]},"assertion":[{"value":"2023-09-21","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}