{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T12:53:53Z","timestamp":1777726433455,"version":"3.51.4"},"reference-count":40,"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"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100003708","name":"Korea Institute of Science and Technology Information","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003708","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100008783","name":"National Research Council of Science and Technology","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100008783","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Computer Physics Communications"],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1016\/j.cpc.2026.110120","type":"journal-article","created":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T23:54:34Z","timestamp":1772841274000},"page":"110120","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["PaScaL_TDMA 2.1: A register-resident multi-GPU tridiagonal matrix solver with optimized communication for large-scale CFD simulations"],"prefix":"10.1016","volume":"323","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4003-6134","authenticated-orcid":false,"given":"Ki-Ha","family":"Kim","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-2366-458X","authenticated-orcid":false,"given":"Dongjin","family":"Lee","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8967-0761","authenticated-orcid":false,"given":"Junhwan","family":"Lee","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6323-9113","authenticated-orcid":false,"given":"Sehyeong","family":"Oh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7022-7911","authenticated-orcid":false,"given":"Seungwon","family":"Lee","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8797-8746","authenticated-orcid":false,"given":"Ji-Hoon","family":"Kang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4948-1250","authenticated-orcid":false,"given":"Jung-Il","family":"Choi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"issue":"7","key":"10.1016\/j.cpc.2026.110120_bib0001","doi-asserted-by":"crossref","DOI":"10.1063\/1.3459156","article-title":"Dynamic global model for large eddy simulation of transient flow","volume":"22","author":"Lee","year":"2010","journal-title":"Phys. Fluids"},{"key":"10.1016\/j.cpc.2026.110120_bib0002","doi-asserted-by":"crossref","DOI":"10.1016\/j.cpc.2023.108785","article-title":"PaScaL_TDMA 2.0: a multi-GPU-based library for solving massive tridiagonal systems","volume":"290","author":"Yang","year":"2023","journal-title":"Comput. Phys. Commun."},{"key":"10.1016\/j.cpc.2026.110120_bib0003","doi-asserted-by":"crossref","DOI":"10.1016\/j.cpc.2020.107722","article-title":"PaScaL_TDMA: a library of parallel and scalable solvers for massive tridiagonal systems","volume":"260","author":"Kim","year":"2021","journal-title":"Comput. Phys. Commun."},{"issue":"1","key":"10.1016\/j.cpc.2026.110120_bib0004","doi-asserted-by":"crossref","first-page":"132","DOI":"10.1006\/jcph.2001.6778","article-title":"An immersed-boundary finite-volume method for simulations of flow in complex geometries","volume":"171","author":"Kim","year":"2001","journal-title":"J. Comput. Phys."},{"key":"10.1016\/j.cpc.2026.110120_bib0005","doi-asserted-by":"crossref","first-page":"301","DOI":"10.1016\/j.ijheatfluidflow.2019.01.010","article-title":"Immersed boundary methods for fluid-structure interaction: a review","volume":"75","author":"Kim","year":"2019","journal-title":"Int. J. Heat Fluid Flow"},{"issue":"3","key":"10.1016\/j.cpc.2026.110120_bib0006","doi-asserted-by":"crossref","first-page":"286","DOI":"10.1109\/12.127441","article-title":"Efficient tridiagonal solvers on multicomputers","volume":"41","author":"Sun","year":"1992","journal-title":"IEEE Trans. Comput."},{"issue":"11","key":"10.1016\/j.cpc.2026.110120_bib0007","doi-asserted-by":"crossref","first-page":"1769","DOI":"10.1016\/0167-8191(95)00033-0","article-title":"Algorithm for solving tridiagonal matrix problems in parallel","volume":"21","author":"Mattor","year":"1995","journal-title":"Parallel Comput."},{"issue":"16","key":"10.1016\/j.cpc.2026.110120_bib0008","doi-asserted-by":"crossref","first-page":"5989","DOI":"10.1016\/j.jcp.2009.05.010","article-title":"High-order compact schemes for incompressible flows: a simple and efficient method with quasi-spectral accuracy","volume":"228","author":"Laizet","year":"2009","journal-title":"J. Comput. Phys."},{"key":"10.1016\/j.cpc.2026.110120_bib0009","doi-asserted-by":"crossref","first-page":"10","DOI":"10.1016\/j.compfluid.2015.04.007","article-title":"A pencil distributed finite difference code for strongly turbulent wall-bounded flows","volume":"116","author":"Poel","year":"2015","journal-title":"Comput. Fluids"},{"issue":"8","key":"10.1016\/j.cpc.2026.110120_bib0010","doi-asserted-by":"crossref","first-page":"1853","DOI":"10.1016\/j.camwa.2018.07.034","article-title":"A FFT-based finite-difference solver for massively-parallel direct numerical simulations of turbulent flows","volume":"76","author":"Costa","year":"2018","journal-title":"Comput. Math. Appl."},{"key":"10.1016\/j.cpc.2026.110120_bib0011","doi-asserted-by":"crossref","DOI":"10.1016\/j.cpc.2023.108779","article-title":"PaScaL_TCS: a versatile solver for large-scale turbulent convective heat transfer problems with temperature-dependent fluid properties","volume":"290","author":"Kim","year":"2023","journal-title":"Comput. Phys. Commun."},{"key":"10.1016\/j.cpc.2026.110120_bib0012","unstructured":"N. Corporation, cuSPARSE library documentation, 2024. https:\/\/docs.nvidia.com\/cuda\/cusparse\/."},{"key":"10.1016\/j.cpc.2026.110120_bib0013","doi-asserted-by":"crossref","first-page":"199","DOI":"10.1016\/j.cpc.2018.03.026","article-title":"AFiD-GPU: a versatile Navier\u2013Stokes solver for wall-bounded turbulent flows on GPU clusters","volume":"229","author":"Zhu","year":"2018","journal-title":"Comput. Phys. Commun."},{"key":"10.1016\/j.cpc.2026.110120_bib0014","doi-asserted-by":"crossref","DOI":"10.1016\/j.cpc.2021.107999","article-title":"A multi-GPU method for ADI-based fractional-step integration of incompressible Navier-Stokes equations","volume":"265","author":"Ha","year":"2021","journal-title":"Comput. Phys. Commun."},{"key":"10.1016\/j.cpc.2026.110120_bib0015","doi-asserted-by":"crossref","DOI":"10.1016\/j.cpc.2025.109747","article-title":"A distributed-memory tridiagonal solver based on a specialised data structure optimised for CPU and GPU architectures","volume":"315","author":"Akkurt","year":"2025","journal-title":"Comput. Phys. Commun."},{"key":"10.1016\/j.cpc.2026.110120_bib0016","first-page":"71","article-title":"Elliptic problems in linear difference equations over a network","volume":"1","author":"Thomas","year":"1949","journal-title":"Watson Sci. Comput. Lab. Rept. Columbia University, New York"},{"key":"10.1016\/j.cpc.2026.110120_bib0017","series-title":"Cray User Group 2010 Conference","first-page":"1","article-title":"2ECOMP&FFT-a highly scalable 2d decomposition library and FFT interface","author":"Li","year":"2010"},{"key":"10.1016\/j.cpc.2026.110120_bib0018","series-title":"Proceedings of the 13th International Conference on Parallel Computing Technologies - Volume 9251","first-page":"489","article-title":"Implementation of a three-phase fluid flow \u201coil-water-gas\u201d numerical model in the LuNA fragmented programming system","author":"Akhmed-Zaki","year":"2015"},{"issue":"1","key":"10.1016\/j.cpc.2026.110120_bib0019","doi-asserted-by":"crossref","first-page":"95","DOI":"10.1145\/321250.321259","article-title":"A fast direct solution of Poisson\u2019s equation using Fourier analysis","volume":"12","author":"Hockney","year":"1965","journal-title":"J. ACM (JACM)"},{"key":"10.1016\/j.cpc.2026.110120_bib0020","series-title":"Parallel Computers: Architecture, Programming and Algorithms","author":"Hockney","year":"1981"},{"issue":"4","key":"10.1016\/j.cpc.2026.110120_bib0021","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/2830568","article-title":"Manycore algorithms for batch scalar and block tridiagonal solvers","volume":"42","author":"Laszlo","year":"2016","journal-title":"ACM Trans. Math. Softw."},{"issue":"4","key":"10.1016\/j.cpc.2026.110120_bib0022","doi-asserted-by":"crossref","first-page":"31:1","DOI":"10.1145\/2830568","article-title":"Manycore algorithms for batch scalar and block tridiagonal solvers","volume":"42","author":"L\u00e1szl\u00f3","year":"2016","journal-title":"ACM Trans. Math. Softw."},{"key":"10.1016\/j.cpc.2026.110120_bib0023","unstructured":"N. Corporation, CUDA fortran programming guide, 2024. https:\/\/docs.nvidia.com\/hpc-sdk\/compilers\/cuda-fortran-prog-guide\/."},{"key":"10.1016\/j.cpc.2026.110120_bib0024","unstructured":"ISO\/IEC, ISO\/IEC 1539-1:2018 information technology \u2014 programming languages \u2014 fortran \u2014 part 1: base language, 2018."},{"key":"10.1016\/j.cpc.2026.110120_bib0025","unstructured":"I. Corporation, Intel xeon gold 6148 processor specifications, 2017. https:\/\/www.intel.com\/content\/www\/us\/en\/products\/sku\/120489\/intel-xeon-gold-6148-processor-27-5m-cache-2-40-ghz\/specifications.html."},{"key":"10.1016\/j.cpc.2026.110120_bib0026","unstructured":"N. Corporation, NVIDIA A100 tensor core GPU datasheet, 2020. https:\/\/www.nvidia.com\/content\/dam\/en-zz\/Solutions\/Data-Center\/a100\/pdf\/nvidia-a100-datasheet-nvidia-us-2188504-web.pdf."},{"key":"10.1016\/j.cpc.2026.110120_bib0027","unstructured":"N. Corporation, NVIDIA H100 tensor core GPU datasheet, 2022. https:\/\/resources.nvidia.com\/en-us-gpu-resources\/h100-datasheet-24306."},{"issue":"10","key":"10.1016\/j.cpc.2026.110120_bib0028","doi-asserted-by":"crossref","first-page":"3670","DOI":"10.1063\/1.1785131","article-title":"An eddy-viscosity subgrid-scale model for turbulent shear flow: algebraic theory and applications","volume":"16","author":"Vreman","year":"2004","journal-title":"Phys. Fluids"},{"issue":"2","key":"10.1016\/j.cpc.2026.110120_bib0029","doi-asserted-by":"crossref","first-page":"308","DOI":"10.1016\/0021-9991(85)90148-2","article-title":"Application of a fractional-step method to incompressible Navier-Stokes equations","volume":"59","author":"Kim","year":"1985","journal-title":"J. Comput. Phys."},{"issue":"1","key":"10.1016\/j.cpc.2026.110120_bib0030","doi-asserted-by":"crossref","first-page":"51","DOI":"10.1006\/jcph.1993.1162","article-title":"An analysis of the fractional step method","volume":"108","author":"Perot","year":"1993","journal-title":"J. Comput. Phys."},{"key":"10.1016\/j.cpc.2026.110120_bib0031","unstructured":"TOP500, TOP500 list samsung electronics SSC-21 system, 2024. Accessed 5 Mar. 2024, https:\/\/www.top500.org\/system\/180041\/."},{"key":"10.1016\/j.cpc.2026.110120_bib0032","unstructured":"Nvidia, GPUDirect RDMA, 2024. https:\/\/docs.nvidia.com\/cuda\/gpudirect-rdma\/index.html."},{"key":"10.1016\/j.cpc.2026.110120_bib0033","doi-asserted-by":"crossref","first-page":"315","DOI":"10.1017\/jfm.2018.787","article-title":"Lock-in regions of laminar flows over a streamwise oscillating circular cylinder","volume":"858","author":"Kim","year":"2019","journal-title":"J. Fluid Mech."},{"key":"10.1016\/j.cpc.2026.110120_bib0034","series-title":"Studying Turbulence Using Numerical Simulation Databases, 2","first-page":"193","article-title":"Eddies, streams, and convergence zones in turbulent flows","author":"Hunt","year":"1988"},{"key":"10.1016\/j.cpc.2026.110120_bib0035","doi-asserted-by":"crossref","first-page":"263","DOI":"10.1017\/jfm.2011.136","article-title":"Direct numerical simulation of the flow over a sphere at Re=3700","volume":"679","author":"Rodriduez","year":"2011","journal-title":"J. Fluid Mech."},{"issue":"11","key":"10.1016\/j.cpc.2026.110120_bib0036","doi-asserted-by":"crossref","first-page":"3260","DOI":"10.1063\/1.866937","article-title":"Observations of the frequencies in a sphere wake and of drag increase by acoustic excitation","volume":"31","author":"Kim","year":"1988","journal-title":"Phys. Fluids"},{"issue":"4","key":"10.1016\/j.cpc.2026.110120_bib0037","doi-asserted-by":"crossref","first-page":"386","DOI":"10.1115\/1.2909415","article-title":"A study on vortex shedding from spheres in a uniform flow","volume":"112","author":"Sakamoto","year":"1990","journal-title":"J. Fluids Eng."},{"issue":"1","key":"10.1016\/j.cpc.2026.110120_bib0038","doi-asserted-by":"crossref","DOI":"10.1063\/1.2166454","article-title":"Vortical structures behind a sphere at subcritical Reynolds numbers","volume":"18","author":"Yun","year":"2006","journal-title":"Phys. Fluids"},{"key":"10.1016\/j.cpc.2026.110120_bib0039","series-title":"Boundary-Layer Theory","author":"Schlichting","year":"1979"},{"key":"10.1016\/j.cpc.2026.110120_bib0040","series-title":"Introduction to Thermodynamics and Heat Transfer","author":"Cengel","year":"2007"}],"container-title":["Computer Physics Communications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0010465526001025?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0010465526001025?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T10:46:28Z","timestamp":1777459588000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0010465526001025"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":40,"alternative-id":["S0010465526001025"],"URL":"https:\/\/doi.org\/10.1016\/j.cpc.2026.110120","relation":{},"ISSN":["0010-4655"],"issn-type":[{"value":"0010-4655","type":"print"}],"subject":[],"published":{"date-parts":[[2026,6]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"PaScaL_TDMA 2.1: A register-resident multi-GPU tridiagonal matrix solver with optimized communication for large-scale CFD simulations","name":"articletitle","label":"Article Title"},{"value":"Computer Physics Communications","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.cpc.2026.110120","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":"110120"}}