{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T18:03:48Z","timestamp":1780423428902,"version":"3.54.1"},"reference-count":51,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"}],"funder":[{"DOI":"10.13039\/100006192","name":"Advanced Scientific Computing Research","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006192","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006234","name":"Sandia National Laboratories","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006234","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Parallel Computing"],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1016\/j.parco.2026.103194","type":"journal-article","created":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T07:26:47Z","timestamp":1772782007000},"page":"103194","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["ShyLU-node: On-node scalable solvers and preconditioners: Recent progress and current performance"],"prefix":"10.1016","volume":"128","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-7248-573X","authenticated-orcid":false,"given":"Ichitaro","family":"Yamazaki","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nathan","family":"Ellingwood","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sivasankaran","family":"Rajamanickam","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.parco.2026.103194_b1","series-title":"Trilinos: Enabling scientific computing across diverse hardware architectures at scale","author":"Mayr","year":"2025"},{"key":"10.1016\/j.parco.2026.103194_b2","unstructured":"The Trilinos Project Team, The Trilinos Project Website, URL https:\/\/trilinos.github.io."},{"key":"10.1016\/j.parco.2026.103194_b3","series-title":"Domain Decomposition Methods in Science and Engineering XXV","first-page":"176","article-title":"FROSch: A fast and robust overlapping Schwarz domain decomposition preconditioner based on xpetra in trilinos","author":"Heinlein","year":"2020"},{"key":"10.1016\/j.parco.2026.103194_b4","series-title":"MueLu User\u2019s Guide","author":"B.-Vergiat","year":"2019"},{"issue":"4","key":"10.1016\/j.parco.2026.103194_b5","doi-asserted-by":"crossref","first-page":"805","DOI":"10.1109\/TPDS.2021.3097283","article-title":"Kokkos 3: Programming model extensions for the exascale era","volume":"33","author":"Trott","year":"2022","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"issue":"2","key":"10.1016\/j.parco.2026.103194_b6","doi-asserted-by":"crossref","first-page":"C169","DOI":"10.1137\/140968896","article-title":"Fine-grained parallel incomplete LU factorization","volume":"37","author":"Chow","year":"2015","journal-title":"SIAM J. Sci. Comput."},{"key":"10.1016\/j.parco.2026.103194_b7","doi-asserted-by":"crossref","unstructured":"K. Kim, H.C. Edwards, S. Rajamanickam, Tacho: Memory-Scalable Task Parallel Sparse Cholesky Factorization, in: 2018 IEEE International Parallel and Distributed Processing Symposium Workshops, IPDPSW, 2018, pp. 550\u2013559.","DOI":"10.1109\/IPDPSW.2018.00094"},{"key":"10.1016\/j.parco.2026.103194_b8","doi-asserted-by":"crossref","unstructured":"J.D. Booth, S. Rajamanickam, H. Thornquist, Basker: A Threaded Sparse LU Factorization Utilizing Hierarchical Parallelism and Data Layouts, in: 2016 IEEE International Parallel and Distributed Processing Symposium Workshops, IPDPSW, 2016, pp. 673\u2013682.","DOI":"10.1109\/IPDPSW.2016.92"},{"key":"10.1016\/j.parco.2026.103194_b9","article-title":"Cross platform fine grained ILU and ILDL factorizations using kokkos","author":"Patel","year":"2015","journal-title":"Proc. CCR"},{"key":"10.1016\/j.parco.2026.103194_b10","series-title":"Parallel Computing","first-page":"165","article-title":"The xyce parallel electronic simulator \u2013 an overview","author":"Hutchinson","year":"2002"},{"key":"10.1016\/j.parco.2026.103194_b11","unstructured":"Xyce: Parallel electronic simulation, URL https:\/\/xyce.sandia.gov."},{"issue":"9","key":"10.1016\/j.parco.2026.103194_b12","doi-asserted-by":"crossref","first-page":"3747","DOI":"10.5194\/gmd-11-3747-2018","article-title":"MPAS-Albany Land Ice (MALI): A variable-resolution ice sheet model for earth system modeling using voronoi grids","volume":"11","author":"Hoffman","year":"2018","journal-title":"Geosci. Model. Dev."},{"key":"10.1016\/j.parco.2026.103194_b13","unstructured":"Albany multiphysics code, URL http:\/\/sandialabs.github.io\/Albany\/."},{"key":"10.1016\/j.parco.2026.103194_b14","series-title":"Performance of Aria running on ATS-2","author":"Clausen","year":"2022"},{"issue":"3","key":"10.1016\/j.parco.2026.103194_b15","doi-asserted-by":"crossref","first-page":"605","DOI":"10.1137\/0905043","article-title":"Direct methods for solving sparse systems of linear equations","volume":"5","author":"Duff","year":"1984","journal-title":"SIAM J. Sci. Stat. Comput."},{"key":"10.1016\/j.parco.2026.103194_b16","doi-asserted-by":"crossref","first-page":"383","DOI":"10.1017\/S0962492916000076","article-title":"A survey of direct methods for sparse linear systems","volume":"25","author":"Davis","year":"2016","journal-title":"Acta Numer."},{"issue":"4","key":"10.1016\/j.parco.2026.103194_b17","doi-asserted-by":"crossref","first-page":"915","DOI":"10.1137\/S0895479897317685","article-title":"An asynchronous parallel supernodal algorithm for sparse Gaussian elimination","volume":"20","author":"Demmel","year":"1999","journal-title":"SIAM J. Matrix Anal. Appl."},{"issue":"2","key":"10.1016\/j.parco.2026.103194_b18","doi-asserted-by":"crossref","first-page":"187","DOI":"10.1016\/S0167-8191(01)00135-1","article-title":"Two-level dynamic scheduling in PARDISO: Improved scalability on shared memory multiprocessing systems","volume":"28","author":"Schenk","year":"2002","journal-title":"Parallel Comput."},{"issue":"1","key":"10.1016\/j.parco.2026.103194_b19","doi-asserted-by":"crossref","first-page":"69","DOI":"10.1016\/S0167-739X(00)00076-5","article-title":"PARDISO: A high-performance serial and parallel sparse linear solver in semiconductor device simulation","volume":"18","author":"Schenk","year":"2001","journal-title":"Future Gener. Comput. Syst."},{"issue":"3","key":"10.1016\/j.parco.2026.103194_b20","doi-asserted-by":"crossref","DOI":"10.1145\/1391989.1391995","article-title":"Algorithm 887: CHOLMOD, supernodal sparse cholesky factorization and update\/downdate","volume":"35","author":"Chen","year":"2008","journal-title":"ACM Trans. Math. Software"},{"key":"10.1016\/j.parco.2026.103194_b21","unstructured":"NVIDIA, cuSOLVER: Direct Linear Solvers on NVIDIA GPUs, https:\/\/developer.nvidia.com\/cusolver."},{"key":"10.1016\/j.parco.2026.103194_b22","unstructured":"NVIDIA, NVIDIA cuDSS: Direct Sparse Solver library on NVIDIA GPUs, https:\/\/developer.nvidia.com\/cudss."},{"key":"10.1016\/j.parco.2026.103194_b23","unstructured":"Advanced Micro Devices (AMD), rocSOLVER software for AMD ROCm platform, https:\/\/rocm.docs.amd.com\/projects\/rocSOLVER."},{"key":"10.1016\/j.parco.2026.103194_b24","doi-asserted-by":"crossref","first-page":"2:1","DOI":"10.1145\/3480935","article-title":"Ginkgo: A modern linear operator algebra framework for high performance computing","volume":"48","author":"Anzt","year":"2022","journal-title":"ACM Trans. Math. Software"},{"key":"10.1016\/j.parco.2026.103194_b25","series-title":"Kokkos Kernels: Performance portable sparse\/dense linear algebra and graph kernels","author":"Rajamanickam","year":"2021"},{"issue":"3","key":"10.1016\/j.parco.2026.103194_b26","first-page":"241","article-title":"Amesos2 and Belos: Direct and iterative solvers for large sparse linear systems","volume":"20","author":"Bavier","year":"2012","journal-title":"Sci. Program."},{"issue":"3","key":"10.1016\/j.parco.2026.103194_b27","doi-asserted-by":"crossref","DOI":"10.1145\/1824801.1824814","article-title":"Algorithm 907: KLU, a direct sparse solver for circuit simulation problems","volume":"37","author":"Davis","year":"2010","journal-title":"ACM Trans. Math. Software"},{"key":"10.1016\/j.parco.2026.103194_b28","series-title":"SuperLU Users\u2019 Guide","author":"Li","year":"1999"},{"issue":"2","key":"10.1016\/j.parco.2026.103194_b29","doi-asserted-by":"crossref","first-page":"501","DOI":"10.1016\/S0045-7825(99)00242-X","article-title":"Multifrontal parallel distributed symmetric and unsymmetric solvers","volume":"184","author":"Amestoy","year":"2000","journal-title":"Comput. Methods Appl. Mech. Engrg."},{"key":"10.1016\/j.parco.2026.103194_b30","series-title":"Ifpack2 User\u2019s Guide 1.0","author":"Prokopenko","year":"2016"},{"issue":"5","key":"10.1016\/j.parco.2026.103194_b31","doi-asserted-by":"crossref","first-page":"S307","DOI":"10.1137\/15M1017946","article-title":"Teko: A block preconditioning capability with concrete example applications in Navier-Stokes and MHD","volume":"38","author":"Cyr","year":"2016","journal-title":"SIAM J. Sci. Comput."},{"issue":"2","key":"10.1016\/j.parco.2026.103194_b32","article-title":"Tpetra, and the use of generic programming in scientific computing","volume":"20","author":"Baker","year":"2012","journal-title":"Sci. Program."},{"key":"10.1016\/j.parco.2026.103194_b33","series-title":"Towards Sustainable Scientific Workflows: DevOps Infrastructure Development in the Engineering Common Model Framework Project","author":"Milewicz","year":"2022"},{"issue":"2","key":"10.1016\/j.parco.2026.103194_b34","doi-asserted-by":"crossref","first-page":"137","DOI":"10.1145\/355780.355785","article-title":"An implementation of Tarjan\u2019s algorithm for the block triangularization of a matrix","volume":"4","author":"Duff","year":"1978","journal-title":"ACM Trans. Math. Software"},{"issue":"2","key":"10.1016\/j.parco.2026.103194_b35","doi-asserted-by":"crossref","first-page":"189","DOI":"10.1145\/355780.355790","article-title":"Algorithm 529: Permutations to block triangular form","volume":"4","author":"Duff","year":"1978","journal-title":"ACM Trans. Math. Software"},{"key":"10.1016\/j.parco.2026.103194_b36","doi-asserted-by":"crossref","first-page":"73","DOI":"10.1142\/S0129053389000056","article-title":"Solving sparse triangular linear systems on parallel computers","volume":"1","author":"Anderson","year":"1989","journal-title":"Int. J. High Speed Comput."},{"key":"10.1016\/j.parco.2026.103194_b37","series-title":"METIS: A software package for partitioning unstructured graphs, partitioning meshes, and computing fill-reducing orderings of sparse matrices","author":"Karypis","year":"1997"},{"issue":"3","key":"10.1016\/j.parco.2026.103194_b38","doi-asserted-by":"crossref","first-page":"381","DOI":"10.1145\/1024074.1024081","article-title":"Algorithm 837: AMD, an approximate minimum degree ordering algorithm","volume":"30","author":"Amestoy","year":"2004","journal-title":"ACM Trans. Math. Software"},{"key":"10.1016\/j.parco.2026.103194_b39","series-title":"Simulation and Verification of Electronic and Biological Systems","first-page":"1","article-title":"Parallel transistor-level circuit simulation","author":"Keiter","year":"2011"},{"key":"10.1016\/j.parco.2026.103194_b40","series-title":"Efficient local classification of parity-based material topology","author":"Wong","year":"2026"},{"key":"10.1016\/j.parco.2026.103194_b41","series-title":"Graph Theory and Sparse Matrix Computation","first-page":"141","article-title":"Highly parallel sparse triangular solution","author":"Alvarado","year":"1993"},{"key":"10.1016\/j.parco.2026.103194_b42","doi-asserted-by":"crossref","unstructured":"I. Yamazaki, S. Rajamanickam, N. Ellingwood, Performance Portable Supernode-Based Sparse Triangular Solver for Manycore Architectures, in: 49th International Conference on Parallel Processing - ICPP, 2020.","DOI":"10.1145\/3404397.3404428"},{"key":"10.1016\/j.parco.2026.103194_b43","series-title":"Revolutionary speedups in SIERRA structural dynamics enhance mission impact","author":"Vo","year":"2022"},{"key":"10.1016\/j.parco.2026.103194_b44","series-title":"Plato optimization-based design","author":"Hardesty","year":"2023"},{"key":"10.1016\/j.parco.2026.103194_b45","series-title":"CFD simulations with panzer","author":"Glasby","year":"2022"},{"key":"10.1016\/j.parco.2026.103194_b46","doi-asserted-by":"crossref","first-page":"856","DOI":"10.1137\/0907058","article-title":"GMRES: A generalized minimal residual algorithm for solving nonsymmetric linear systems","volume":"7","author":"Saad","year":"1986","journal-title":"SIAM J. Sci. Stat. Comput."},{"issue":"2","key":"10.1016\/j.parco.2026.103194_b47","doi-asserted-by":"crossref","first-page":"332","DOI":"10.1177\/1094342017749957","article-title":"Toward performance portability of the Albany finite element analysis code using the Kokkos library","volume":"33","author":"Demeshko","year":"2019","journal-title":"Int. J. High Perform. Comput. Appl."},{"issue":"5","key":"10.1016\/j.parco.2026.103194_b48","doi-asserted-by":"crossref","first-page":"600","DOI":"10.1177\/10943420231183688","article-title":"Performance portable ice-sheet modeling with MALI","volume":"37","author":"Watkins","year":"2023","journal-title":"Int. J. High Perform. Comput. Appl."},{"key":"10.1016\/j.parco.2026.103194_b49","doi-asserted-by":"crossref","unstructured":"I. Yamazaki, A. Heinlein, S. Rajamanickam, An Experimental Study of Two-level Schwarz Domain-Decomposition Preconditioners on GPUs, in: 2023 IEEE International Parallel and Distributed Processing Symposium, IPDPS, 2023, pp. 680\u2013689.","DOI":"10.1109\/IPDPS54959.2023.00073"},{"issue":"5","key":"10.1016\/j.parco.2026.103194_b50","doi-asserted-by":"crossref","first-page":"753","DOI":"10.1016\/0167-8191(94)90004-3","article-title":"Scalable iterative solution of sparse linear systems","volume":"20","author":"Jones","year":"1994","journal-title":"Parallel Comput."},{"issue":"150","key":"10.1016\/j.parco.2026.103194_b51","doi-asserted-by":"crossref","first-page":"473","DOI":"10.1090\/S0025-5718-1980-0559197-0","article-title":"An incomplete factorization technique for positive definite linear systems","volume":"34","author":"Manteuffel","year":"1980","journal-title":"Math. Comp."}],"container-title":["Parallel Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167819126000128?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167819126000128?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T17:29:18Z","timestamp":1780421358000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0167819126000128"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":51,"alternative-id":["S0167819126000128"],"URL":"https:\/\/doi.org\/10.1016\/j.parco.2026.103194","relation":{},"ISSN":["0167-8191"],"issn-type":[{"value":"0167-8191","type":"print"}],"subject":[],"published":{"date-parts":[[2026,6]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"ShyLU-node: On-node scalable solvers and preconditioners: Recent progress and current performance","name":"articletitle","label":"Article Title"},{"value":"Parallel Computing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.parco.2026.103194","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"103194"}}