On the improvement of a scalable sparse direct solver for unsymmetrical linear equations

Basit Öğe Kaydı
dc.authoridÇelebi, Mustafa Serdar/0000-0003-4566-0216|Duran, Ahmet/0000-0001-9835-0006|Tuncel, Mehmet/0000-0002-6798-2876
dc.authorwosidÇelebi, Mustafa Serdar/AAJ-5557-2020
dc.authorwosidDuran, Ahmet/D-9386-2015
dc.authorwosidOztoprak, Figen/ABH-1969-2021
dc.authorwosidTuncel, Mehmet/ABD-7341-2020
dc.contributor.authorCelebi, M. Serdar
dc.contributor.authorDuran, Ahmet
dc.contributor.authorOztoprak, Figen
dc.contributor.authorTuncel, Mehmet
dc.contributor.authorAkaydin, Bora
dc.date.accessioned2024-07-18T20:42:17Z
dc.date.available2024-07-18T20:42:17Z
dc.date.issued2017
dc.departmentİstanbul Bilgi Üniversitesien_US
dc.description.abstractThis paper focuses on the application level improvements in a sparse direct solver specifically used for large-scale unsymmetrical linear equations resulting from unstructured mesh discretization of coupled elliptic/hyperbolic PDEs. Existing sparse direct solvers are designed for distributed server systems taking advantage of both distributed memory and processing units. We conducted extensive numerical experiments with three state-of-the-art direct linear solvers that can work on distributed-memory parallel architectures; namely, MUMPS(MUMPS solver website, http://graal.ens-lyon.fr/MUMPS), WSMP (Technical Report TR RC-21886, IBM, Watson Research Center, Yorktown Heights, 2000), and SUPERLU_DIST (ACM Trans Math Softw 29(2): 110-140, 2003). The performance of these solvers was analyzed in detail, using advanced analysis tools such as Tuning and Analysis Utilities (TAU) and Performance Application Programming Interface (PAPI). The performance is evaluated with respect to robustness, speed, scalability, and efficiency in CPU and memory usage. We have determined application level issues that we believe they can improve the performance of a distributed-shared memory hybrid variant of this solver, which is proposed as an alternative solver [SuperLU_MCDT (Many-Core Distributed)] in this paper. The new solver utilizing the MPI/OpenMP hybrid programming is specifically tuned to handle large unsymmetrical systems arising in reservoir simulations so that higher performance and better scalability can be achieved for a large distributed computing system with many nodes of multicore processors. Two main tasks are accomplished during this study: (i) comparisons of public domain solver algorithms; existing state-of-the-art direct sparse linear system solvers are investigated and their performance and weaknesses based on test cases are analyzed, (ii) improvement of direct sparse solver algorithm (SuperLU_MCDT) for many-core distributed systems is achieved. We provided results of numerical tests that were run on up to 16,384 cores, and used many sets of test matrices for reservoir simulations with unstructured meshes. The numerical results showed that SuperLU_MCDT can outperform SuperLU_DIST 3.3 in terms of both speed and robustness.en_US
dc.description.sponsorshipUHeM (National High Performance Computing Center of Turkey) [RI-28349]; Aramco Overseas Company B.V. [6600028651]en_US
dc.description.sponsorshipAuthors acknowledge for the computing resources allocated by PRACE Research Infrastructures 'Hydra' at RZG (Rechenzentrum Garching) Germany, and 'Karadeniz' at UHeM (National High Performance Computing Center of Turkey) under Grant Agreement RI-28349. The authors thank to Aramco Overseas Company B.V. for their financial support under contract number 6600028651. The authors appreciate the helpful comments and suggestions by the Editor-in-Chief of The Journal of Supercomputing, Prof. Hamid R. Arabnia, and anonymous referees.en_US
dc.identifier.doi10.1007/s11227-016-1892-7
dc.identifier.endpage1904en_US
dc.identifier.issn0920-8542
dc.identifier.issn1573-0484
dc.identifier.issue5en_US
dc.identifier.scopus2-s2.0-84992046878en_US
dc.identifier.scopusqualityQ2en_US
dc.identifier.startpage1852en_US
dc.identifier.urihttps://doi.org/10.1007/s11227-016-1892-7
dc.identifier.urihttps://hdl.handle.net/11411/7224
dc.identifier.volume73en_US
dc.identifier.wosWOS:000404596100005en_US
dc.identifier.wosqualityQ2en_US
dc.indekslendigikaynakWeb of Scienceen_US
dc.indekslendigikaynakScopusen_US
dc.language.isoenen_US
dc.publisherSpringeren_US
dc.relation.ispartofJournal of Supercomputingen_US
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.subjectParallel Linear Direct Solveren_US
dc.subjectSparse Direct Solveren_US
dc.subjectMany-Core Distributed Solveren_US
dc.subjectReservoir Simulationsen_US
dc.subjectLarge Scale Simulationsen_US
dc.subjectSymbolic Factorizationen_US
dc.subjectNumerical Factorizationen_US
dc.subjectScalabilityen_US
dc.subjectLinear Equationsen_US
dc.subjectSuperluen_US
dc.subjectParallelen_US
dc.subjectAlgorithmen_US
dc.titleOn the improvement of a scalable sparse direct solver for unsymmetrical linear equationsen_US
dc.typeArticleen_US

Dosyalar

Koleksiyon

Web of Science Indexed Publications
Scopus Indexed Publications