{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T13:40:13Z","timestamp":1755870013540,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":63,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:00:00Z","timestamp":1755820800000},"content-version":"vor","delay-in-days":75,"URL":"http:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2343865, 2139536"],"award-info":[{"award-number":["2343865, 2139536"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Department of Energy: Office of Advanced Scientific Computing Research","award":["DE-AC36-08GO28308"],"award-info":[{"award-number":["DE-AC36-08GO28308"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,6,8]]},"DOI":"10.1145\/3721145.3730413","type":"proceedings-article","created":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T12:57:17Z","timestamp":1755867437000},"page":"308-323","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Statistical Treatment of Variable MPI Latencies and MPI-Communication Hiding for Matrix-Free Finite Element Operators"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3602-2143","authenticated-orcid":false,"given":"Max","family":"Heldman","sequence":"first","affiliation":[{"name":"Department of Mathematics, Virginia Tech, Blacksburg, VA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6563-9265","authenticated-orcid":false,"given":"Johann","family":"Rudi","sequence":"additional","affiliation":[{"name":"Department of Mathematics, Virginia Tech, Blacksburg, VA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6407-2423","authenticated-orcid":false,"given":"Julie","family":"Bessac","sequence":"additional","affiliation":[{"name":"Computational Science Center, National Renewable Energy Laboratory, Golden, Colorado, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,8,22]]},"reference":[{"key":"e_1_3_3_1_2_2","doi-asserted-by":"crossref","unstructured":"Laksono Adhianto Sinchan Banerjee Mike Fagan Mark Krentel Gabriel Marin John Mellor-Crummey and Nathan\u00a0R Tallent. 2010. HPCToolkit: Tools for performance analysis of optimized parallel programs. Concurrency and Computation: Practice and Experience 22 6 (2010) 685\u2013701.","DOI":"10.1002\/cpe.1553"},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2014.18"},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"crossref","unstructured":"Hirotugu Akaike. 1974. A new look at the statistical model identification. IEEE Transactions on Automatic Control 19 6 (1974) 716\u2013723.","DOI":"10.1109\/TAC.1974.1100705"},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"crossref","unstructured":"Burak Aksar Efe Sencan Benjamin Schwaller Omar Aaziz Vitus\u00a0J Leung Jim Brandt Brian Kulis Manuel Egele and Ayse\u00a0K Coskun. 2024. Runtime Performance Anomaly Diagnosis in Production HPC Systems Using Active Learning. IEEE Transactions on Parallel and Distributed Systems (2024).","DOI":"10.1109\/TPDS.2024.3365462"},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-78713-4_11"},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"crossref","unstructured":"Daniel Arndt Wolfgang Bangerth Denis Davydov Timo Heister Luca Heltai Martin Kronbichler Matthias Maier Jean-Paul Pelteret Bruno Turcksin and David Wells. 2021. The deal.II finite element library: Design features and insights. Computers & Mathematics with Applications 81 (2021) 407\u2013422.","DOI":"10.1016\/j.camwa.2020.02.022"},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1145\/2934872.2934884"},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.2172\/2337606"},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"crossref","unstructured":"Wolfgang Bangerth Ralf Hartmann and Guido Kanschat. 2007. deal.II -\u2014 A general-purpose object-oriented finite element library. ACM Transactions on Mathematical Software (TOMS) 33 4 (2007) 24\u2013es.","DOI":"10.1145\/1268776.1268779"},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"crossref","unstructured":"Leonard\u00a0E. Baum and J.\u00a0A. Eagon. 1967. An inequality with applications to statistical estimation for probabilistic functions of Markov processes and to a model for ecology. Bull. Amer. Math. Soc. 73 6 (1967) 360\u2013363.","DOI":"10.1090\/S0002-9904-1967-11751-8"},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"crossref","unstructured":"Leonard\u00a0E Baum and Ted Petrie. 1966. Statistical inference for probabilistic functions of finite state Markov chains. The Annals of Mathematical Statistics 37 6 (1966) 1554\u20131563.","DOI":"10.1214\/aoms\/1177699147"},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1145\/2503210.2503247"},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1145\/1947940.1948050"},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1145\/1755913.1755926"},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/AICAS.2019.8771527"},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"crossref","unstructured":"Carsten Burstedde Lucas\u00a0C. Wilcox and Omar Ghattas. 2011. p4est: Scalable Algorithms for Parallel Adaptive Mesh Refinement on Forests of Octrees. SIAM Journal on Scientific Computing 33 3 (2011) 1103\u20131133. https:\/\/doi.org\/10.1137\/100791634","DOI":"10.1137\/100791634"},{"key":"e_1_3_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1145\/3295500.3356215"},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1145\/3126908.3126926"},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"crossref","unstructured":"Arthur\u00a0P Dempster Nan\u00a0M Laird and Donald\u00a0B Rubin. 1977. Maximum likelihood from incomplete data via the EM algorithm. Journal of the Royal Statistical Society: Series B (Methodological) 39 1 (1977) 1\u201322.","DOI":"10.1111\/j.2517-6161.1977.tb01600.x"},{"key":"e_1_3_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511546792"},{"key":"e_1_3_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1145\/3330345.3330358"},{"key":"e_1_3_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.5555\/1413370.1413390"},{"key":"e_1_3_3_1_24_2","doi-asserted-by":"crossref","unstructured":"Paul Fischer Stefan Kerkemeier Misun Min Yu-Hsiang Lan Malachi Phillips Thilina Rathnayake Elia Merzari Ananias Tomboulides Ali Karakus Noel Chalmers and Tim Warburton. 2022. NekRS a GPU-accelerated spectral element Navier\u2013Stokes solver. Parallel Comput. 114 (2022) 102982.","DOI":"10.1016\/j.parco.2022.102982"},{"key":"e_1_3_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/125\/1\/012076"},{"key":"e_1_3_3_1_26_2","volume-title":"Nek5000","author":"Fischer Paul","year":"2007","unstructured":"Paul Fischer, James Lottes, and Henry Tufo. 2007. Nek5000. Technical Report. Argonne National Laboratory (ANL), Argonne, IL (United States)."},{"key":"e_1_3_3_1_27_2","doi-asserted-by":"crossref","unstructured":"Paul Fischer Misun Min Thilina Rathnayake Som Dutta Tzanio Kolev Veselin Dobrev Jean-Sylvain Camier Martin Kronbichler Tim Warburton Kasia \u015awirydowicz et\u00a0al. 2020. Scalability of high-performance PDE solvers. The International Journal of High Performance Computing Applications 34 5 (2020) 562\u2013586.","DOI":"10.1177\/1094342020915762"},{"key":"e_1_3_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.2514\/6.2015-3049"},{"key":"e_1_3_3_1_29_2","doi-asserted-by":"crossref","unstructured":"G\u00a0David Forney. 1973. The Viterbi algorithm. Proc. IEEE 61 3 (1973) 268\u2013278.","DOI":"10.1109\/PROC.1973.9030"},{"key":"e_1_3_3_1_30_2","volume-title":"Overtime: A Benchmark for Analyzing Performance Variation due to Network Interference.","author":"Grant Ryan","year":"2014","unstructured":"Ryan Grant, Kevin Pedretti, and Ann\u00a0C Gentile. 2014. Overtime: A Benchmark for Analyzing Performance Variation due to Network Interference.Technical Report. Sandia National Lab.(SNL-NM), Albuquerque, NM (United States)."},{"key":"e_1_3_3_1_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER.2017.76"},{"key":"e_1_3_3_1_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/SRDS.2016.017"},{"key":"e_1_3_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.1145\/2807591.2807644"},{"key":"e_1_3_3_1_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2010.12"},{"key":"e_1_3_3_1_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/TEST.2016.7805836"},{"key":"e_1_3_3_1_36_2","unstructured":"Stefan Kerkemeier and et al.2024. gslib v1.0.9 \u2013 Sparse communication library. https:\/\/github.com\/Nek5000\/gslib (Accessed: Dec. 11 2024)."},{"key":"e_1_3_3_1_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER.2017.23"},{"key":"e_1_3_3_1_38_2","doi-asserted-by":"crossref","unstructured":"Martin Kronbichler Timo Heister and Wolfgang Bangerth. 2012. High accuracy mantle convection simulation through modern numerical methods. Geophysical Journal International 191 1 (2012) 12\u201329.","DOI":"10.1111\/j.1365-246X.2012.05609.x"},{"key":"e_1_3_3_1_39_2","doi-asserted-by":"crossref","unstructured":"Martin Kronbichler and Katharina Kormann. 2012. A generic interface for parallel cell-based finite element operator application. Computers & Fluids 63 (2012) 135\u2013147.","DOI":"10.1016\/j.compfluid.2012.04.012"},{"key":"e_1_3_3_1_40_2","doi-asserted-by":"crossref","unstructured":"Zhiling Lan Ziming Zheng and Yawei Li. 2009. Toward automated anomaly identification in large-scale systems. IEEE Transactions on Parallel and Distributed Systems 21 2 (2009) 174\u2013187.","DOI":"10.1109\/TPDS.2009.52"},{"key":"e_1_3_3_1_41_2","doi-asserted-by":"publisher","DOI":"10.1145\/2783258.2788611"},{"key":"e_1_3_3_1_42_2","doi-asserted-by":"publisher","DOI":"10.1145\/3581784.3627038"},{"key":"e_1_3_3_1_43_2","doi-asserted-by":"crossref","unstructured":"Martin Molan Andrea Borghesi Daniele Cesarini Luca Benini and Andrea Bartolini. 2023. RUAD: Unsupervised anomaly detection in HPC systems. Future Generation Computer Systems 141 (2023) 542\u2013554.","DOI":"10.1016\/j.future.2022.12.001"},{"key":"e_1_3_3_1_44_2","doi-asserted-by":"crossref","unstructured":"Peter Munch Timo Heister Laura Prieto\u00a0Saavedra and Martin Kronbichler. 2023. Efficient distributed matrix-free multigrid methods on locally refined meshes for FEM computations. ACM Transactions on Parallel Computing 10 1 (2023) 1\u201338.","DOI":"10.1145\/3580314"},{"key":"e_1_3_3_1_45_2","doi-asserted-by":"publisher","DOI":"10.1145\/2783258.2788624"},{"key":"e_1_3_3_1_46_2","doi-asserted-by":"crossref","unstructured":"Lawrence\u00a0R Rabiner. 1989. A tutorial on hidden Markov models and selected applications in speech recognition. Proc. IEEE 77 2 (1989) 257\u2013286.","DOI":"10.1109\/5.18626"},{"key":"e_1_3_3_1_47_2","doi-asserted-by":"publisher","DOI":"10.1145\/2807591.2807675"},{"key":"e_1_3_3_1_48_2","doi-asserted-by":"crossref","unstructured":"Johann Rudi Yu-Hsuan Shih and Georg Stadler. 2020. Advanced Newton Methods for Geodynamical Models of Stokes Flow with Viscoplastic Rheologies. Geochemistry Geophysics Geosystems 21 9 (2020). https:\/\/doi.org\/10.1029\/2020GC009059","DOI":"10.1029\/2020GC009059"},{"key":"e_1_3_3_1_49_2","doi-asserted-by":"crossref","unstructured":"Johann Rudi Georg Stadler and Omar Ghattas. 2017. Weighted BFBT Preconditioner for Stokes Flow Problems with Highly Heterogeneous Viscosity. SIAM Journal on Scientific Computing 39 5 (2017) S272\u2013S297. https:\/\/doi.org\/10.1137\/16M108450X","DOI":"10.1137\/16M108450X"},{"key":"e_1_3_3_1_50_2","doi-asserted-by":"publisher","unstructured":"P. Sanan S.M. Schnepp and D.A. May. 2016. Pipelined Flexible Krylov Subspace Methods. SIAM Journal on Scientific Computing 38 5 (2016) C441\u2013C470. https:\/\/doi.org\/10.1137\/15M1049130 arXiv:10.1137\/15M1049130","DOI":"10.1137\/15M1049130"},{"key":"e_1_3_3_1_51_2","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2005.1526010"},{"key":"e_1_3_3_1_52_2","doi-asserted-by":"crossref","unstructured":"Ying Sun and Marc\u00a0G Genton. 2011. Functional boxplots. Journal of Computational and Graphical Statistics 20 2 (2011) 316\u2013334.","DOI":"10.1198\/jcgs.2011.09224"},{"key":"e_1_3_3_1_53_2","doi-asserted-by":"publisher","DOI":"10.1145\/3295500.3356168"},{"key":"e_1_3_3_1_54_2","doi-asserted-by":"publisher","DOI":"10.1145\/331532.331599"},{"key":"e_1_3_3_1_55_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-58667-0_19"},{"key":"e_1_3_3_1_56_2","doi-asserted-by":"crossref","unstructured":"Ozan Tuncer Emre Ates Yijia Zhang Ata Turk Jim Brandt Vitus\u00a0J Leung Manuel Egele and Ayse\u00a0K Coskun. 2018. Online diagnosis of performance variation in HPC systems using machine learning. IEEE Transactions on Parallel and Distributed Systems 30 4 (2018) 883\u2013896.","DOI":"10.1109\/TPDS.2018.2870403"},{"key":"e_1_3_3_1_57_2","doi-asserted-by":"publisher","DOI":"10.1145\/3184407.3184427"},{"key":"e_1_3_3_1_58_2","unstructured":"Ingmar Visser and Maarten Speekenbrink. 2021. hmmr v1.0-0 \u2013 Mixture and Hidden Markov Models with R. https:\/\/doi.org\/10.32614\/CRAN.package.hmmr https:\/\/CRAN.R-project.org\/package=hmmr (Accessed: Dec. 15 2024)."},{"key":"e_1_3_3_1_59_2","doi-asserted-by":"crossref","unstructured":"Andrew\u00a0J. Viterbi. 1967. Error bounds for convolutional codes and an asymptotically optimum decoding algorithm. IEEE transactions on Information Theory 13 2 (1967) 260\u2013269.","DOI":"10.1109\/TIT.1967.1054010"},{"key":"e_1_3_3_1_60_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-92040-5_13"},{"key":"e_1_3_3_1_61_2","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2016.63"},{"key":"e_1_3_3_1_62_2","doi-asserted-by":"crossref","unstructured":"Li Yu and Zhiling Lan. 2015. A scalable non-parametric method for detecting performance anomaly in large scale computing. IEEE Transactions on Parallel and Distributed Systems 27 7 (2015) 1902\u20131914.","DOI":"10.1109\/TPDS.2015.2475741"},{"key":"e_1_3_3_1_63_2","doi-asserted-by":"publisher","DOI":"10.1109\/CLOUD.2016.0136"},{"key":"e_1_3_3_1_64_2","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER49012.2020.00026"}],"event":{"name":"ICS '25: 2025 International Conference on Supercomputing","location":"Salt Lake City USA","acronym":"ICS '25","sponsor":["SIGARCH ACM Special Interest Group on Computer Architecture"]},"container-title":["Proceedings of the 39th ACM International Conference on Supercomputing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3721145.3730413","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3721145.3730413","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T13:04:16Z","timestamp":1755867856000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3721145.3730413"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,8]]},"references-count":63,"alternative-id":["10.1145\/3721145.3730413","10.1145\/3721145"],"URL":"https:\/\/doi.org\/10.1145\/3721145.3730413","relation":{},"subject":[],"published":{"date-parts":[[2025,6,8]]},"assertion":[{"value":"2025-08-22","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}