{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:14:09Z","timestamp":1750220049491,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":35,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,2,21]],"date-time":"2023-02-21T00:00:00Z","timestamp":1676937600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"the National Natural Science Foundation of China","award":["62072146"],"award-info":[{"award-number":["62072146"]}]},{"name":"The Key Research and Development Program of Zhejiang Province","award":["2021C03187"],"award-info":[{"award-number":["2021C03187"]}]},{"name":"the National Key Research and Development Program of China","award":["2020YFB0204802"],"award-info":[{"award-number":["2020YFB0204802"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,2,25]]},"DOI":"10.1145\/3572848.3577517","type":"proceedings-article","created":{"date-parts":[[2023,2,21]],"date-time":"2023-02-21T16:02:30Z","timestamp":1676995350000},"page":"135-147","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["A Scalable Hybrid Total FETI Method for Massively Parallel FEM Simulations"],"prefix":"10.1145","author":[{"given":"Kehao","family":"Lin","sequence":"first","affiliation":[{"name":"Hangzhou Dianzi University, Hangzhou, China and Computer Network Information Center, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chunbao","family":"Zhou","sequence":"additional","affiliation":[{"name":"Computer Network Information Center, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yan","family":"Zeng","sequence":"additional","affiliation":[{"name":"Hangzhou Dianzi University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ningming","family":"Nie","sequence":"additional","affiliation":[{"name":"Computer Network Information Center, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jue","family":"Wang","sequence":"additional","affiliation":[{"name":"Computer Network Information Center, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shigang","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yangde","family":"Feng","sequence":"additional","affiliation":[{"name":"Computer Network Information Center, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yangang","family":"Wang","sequence":"additional","affiliation":[{"name":"Computer Network Information Center, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kehan","family":"Yao","sequence":"additional","affiliation":[{"name":"Hangzhou Dianzi University, Hangzhou, China and Computer Network Information Center, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tiechui","family":"Yao","sequence":"additional","affiliation":[{"name":"Computer Network Information Center, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jilin","family":"Zhang","sequence":"additional","affiliation":[{"name":"Hangzhou Dianzi University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jian","family":"Wan","sequence":"additional","affiliation":[{"name":"Hangzhou Dianzi University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,2,21]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"AMD. 2019. AMD GPU basis. https:\/\/www.olcf.ornl.gov\/wp-content\/uploads\/2019\/10\/ORNL_Application_Readiness_Workshop-AMD_GPU_Basics.pdf"},{"key":"e_1_3_2_1_2_1","unstructured":"AMD. 2019. Using with AMD's HIP on Frontier. https:\/\/www.olcf.ornl.gov\/wp-content\/uploads\/2019\/10\/CAAR_HIP_on_Frontier.pdf"},{"key":"e_1_3_2_1_3_1","unstructured":"AMD. 2020. Rocm documentation. https:\/\/rocblas.readthedocs.io\/en\/master\/"},{"key":"e_1_3_2_1_4_1","volume-title":"Modifications to Graph Partitioning Tools for use with FETI methods. Domain Decomposition Methods in Science and Engineering","author":"Bhardwaj MK","year":"2002","unstructured":"MK Bhardwaj and DM Day. 2002. Modifications to Graph Partitioning Tools for use with FETI methods. Domain Decomposition Methods in Science and Engineering (2002), 195."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","unstructured":"M Bo\u0161ansk\u1ef3 and B Patz\u00e1k. 2019. ON TUNING OF FINITE ELEMENT LOAD BALANCING FRAMEWORK. 10.21495\/71-0-61","DOI":"10.21495\/71-0-61"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC43674.2020.9286214"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/HiPC.2014.7116878"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1002\/cnm.881"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.finel.2020.103484"},{"key":"e_1_3_2_1_11_1","volume-title":"The two-level FETI method for static and dynamic plate problems Part I: An optimal iterative solver for biharmonic systems. Computer methods in applied mechanics and engineering 155, 1--2","author":"Farhat Charbel","year":"1998","unstructured":"Charbel Farhat and Jan Mandel. 1998. The two-level FETI method for static and dynamic plate problems Part I: An optimal iterative solver for biharmonic systems. Computer methods in applied mechanics and engineering 155, 1--2 (1998), 129--151."},{"key":"e_1_3_2_1_12_1","volume-title":"Optimal convergence properties of the FETI domain decomposition method. Computer methods in applied mechanics and engineering 115, 3--4","author":"Farhat Charbel","year":"1994","unstructured":"Charbel Farhat, Jan Mandel, and Francois Xavier Roux. 1994. Optimal convergence properties of the FETI domain decomposition method. Computer methods in applied mechanics and engineering 115, 3--4 (1994), 365--385."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1002\/nme.1620320604"},{"key":"e_1_3_2_1_14_1","unstructured":"Jos\u00e9 Luis Gonz\u00e1lez Garc\u00eda Ramin Yahyapour and Andrei Tchernykh. 2013. Load balancing for parallel computations with the finite element method. (2013)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1002\/nme.4946"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1002\/gamm.202100001"},{"key":"e_1_3_2_1_17_1","first-page":"1","article-title":"Finite element modeling and simulation of car crash","volume":"3","author":"Hickey Andrew","year":"2017","unstructured":"Andrew Hickey and Shaoping Xiao. 2017. Finite element modeling and simulation of car crash. Int. J. Mod. Stud. Mech. Eng 3 (2017), 1--5.","journal-title":"Int. J. Mod. Stud. Mech. Eng"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2938011"},{"key":"e_1_3_2_1_19_1","volume-title":"A software package for partitioning unstructured graphs, partitioning meshes, and computing fill-reducing orderings of sparse matrices","author":"Karypis George","year":"1998","unstructured":"George Karypis and Vipin Kumar. 1998. A software package for partitioning unstructured graphs, partitioning meshes, and computing fill-reducing orderings of sparse matrices. University of Minnesota, Department of Computer Science and Engineering, Army HPC Research Center, Minneapolis, MN 38 (1998)."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1002\/nme.6237"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1137\/140997907"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1137\/130939675"},{"key":"e_1_3_2_1_23_1","volume-title":"Hybrid total FETI method. PRACE whitepaper","author":"Kozubek T","year":"2012","unstructured":"T Kozubek, M Jaro\u0161lav\u00e1, M Men\u0161\u00edk, and A Markopoulos. 2012. Hybrid total FETI method. PRACE whitepaper (2012)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3480856"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.advengsoft.2017.05.001"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","unstructured":"Satoshi Ohshima Ichitaro Yamazaki Akihiro Ida and Rio Yokota. 2019. Optimization of Numerous Small Dense-Matrix-Vector Multiplications in H-Matrix Arithmetic on GPU. In 2019 IEEE 13th International Symposium on Embedded Multicore\/Many-core Systems-on-Chip (MCSoC). 9--16. 10.1109\/MCSoC.2019.00009","DOI":"10.1109\/MCSoC.2019.00009"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-61142-8_588"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.parco.2016.05.002"},{"volume-title":"High Performance Computing in Science and Engineering, Tom\u00e1\u0161 Kozubek, Radim Blaheta, Jakub \u0160\u00edstek, Miroslav Rozlo\u017en\u00edk, and Martin \u010cerm\u00e1k (Eds.)","author":"R\u00edha Lubom\u00edr","key":"e_1_3_2_1_30_1","unstructured":"Lubom\u00edr R\u00edha, Tom\u00e1\u0161 Brzobohat\u00fd, Alexandros Markopoulos, Tom\u00e1\u0161 Kozubek, Ond\u0159ej Meca, Olaf Schenk, and Wim Vanroose. 2016. Efficient Implementation of Total FETI Solver for Graphic Processing Units Using Schur Complement. In High Performance Computing in Science and Engineering, Tom\u00e1\u0161 Kozubek, Radim Blaheta, Jakub \u0160\u00edstek, Miroslav Rozlo\u017en\u00edk, and Martin \u010cerm\u00e1k (Eds.). Springer International Publishing, Cham, 85--100."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1177\/1094342018798452"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1090\/conm\/218\/03008"},{"key":"e_1_3_2_1_33_1","unstructured":"Chayma Sakouhi Abir Khaldi and Henda Ben Ghezal. 2018. An overview of recent graph partitioning algorithms. In Proceedings of the International Conference on Parallel and Distributed Processing Techniques and Applications (PDPTA). The Steering Committee of The World Congress in Computer Science Computer ... 408--414."},{"key":"e_1_3_2_1_34_1","volume-title":"KaHIP-Karlsruhe High Quality Partitioning. URL http:\/\/algo2.iti.kit.edu\/kahip","author":"Sanders Peter","year":"2016","unstructured":"Peter Sanders and Christian Schulz. 2016. KaHIP-Karlsruhe High Quality Partitioning. URL http:\/\/algo2.iti.kit.edu\/kahip (2016), 31."},{"key":"e_1_3_2_1_35_1","unstructured":"Hans Henrik Brandenborg S\u00f8rensen. 2012. High-Performance Matrix-Vector Multiplication on the GPU. In Euro-Par 2011: Parallel Processing Workshops Michael Alexander Pasqua D'Ambra Adam Belloum George Bosilca Mario Cannataro Marco Danelutto Beniamino Di Martino Michael Gerndt Emmanuel Jeannot Raymond Namyst Jean Roman Stephen L. Scott Jesper Larsson Traff Geoffroy Vall\u00e9e and Josef Weidendorfer (Eds.). Springer Berlin Heidelberg Berlin Heidelberg 377--386."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCS.2018.00091"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2014.06.002"}],"event":{"name":"PPoPP '23: The 28th ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming","sponsor":["SIGPLAN ACM Special Interest Group on Programming Languages","SIGHPC ACM Special Interest Group on High Performance Computing, Special Interest Group on High Performance Computing"],"location":"Montreal QC Canada","acronym":"PPoPP '23"},"container-title":["Proceedings of the 28th ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3572848.3577517","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3572848.3577517","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T18:08:10Z","timestamp":1750183690000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3572848.3577517"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,2,21]]},"references-count":35,"alternative-id":["10.1145\/3572848.3577517","10.1145\/3572848"],"URL":"https:\/\/doi.org\/10.1145\/3572848.3577517","relation":{},"subject":[],"published":{"date-parts":[[2023,2,21]]},"assertion":[{"value":"2023-02-21","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}