Geodesic
Heterogeneous parallel implementation of a multigrid method with full approximation in the NOISETTE code
Matematičeskoe modelirovanie, Tome 36 (2024) no. 2, pp. 129-146.

Voir la notice de l'article provenant de la source Math-Net.Ru

The article is devoted to accelerating simulations of compressible flows on hybrid cluster systems using the full approximation scheme multigrid method (FAS MG). The basic numerical algorithm has the following features: for spatial discretization, unstructured mixed-element meshes and schemes with definition of mesh functions at mesh nodes are used; for temporal discretization, a fully implicit scheme is used. The goal of this work is to achieve acceleration of stationary simulations on both central and graphics processors without significant losses in parallel efficiency. We describe an approach to construct mesh levels; a technique for improving the quality of mesh representation of the geometry of modeled objects; parallel implementation within the framework of complex parallelization, combining MPI for a distributed-memory parallel model, OpenMP for a shared-memory model, and OpenCL for computing on GPUs of various architectures.
Keywords: supercomputer simulation, FAS Multigrid, MPI+OpenMP+OpenCL.
Mots-clés : CFD 
@article{MM_2024_36_2_a7,
     author = {A. V. Gorobets and S. A. Soukov and A. R. Magomedov},
     title = {Heterogeneous parallel implementation of a multigrid method with full approximation in the  {NOISETTE} code},
     journal = {Matemati\v{c}eskoe modelirovanie},
     pages = {129--146},
     publisher = {mathdoc},
     volume = {36},
     number = {2},
     year = {2024},
     language = {ru},
     url = {http://geodesic.mathdoc.fr/item/MM_2024_36_2_a7/}
}
TY  - JOUR
AU  - A. V. Gorobets
AU  - S. A. Soukov
AU  - A. R. Magomedov
TI  - Heterogeneous parallel implementation of a multigrid method with full approximation in the  NOISETTE code
JO  - Matematičeskoe modelirovanie
PY  - 2024
SP  - 129
EP  - 146
VL  - 36
IS  - 2
PB  - mathdoc
UR  - http://geodesic.mathdoc.fr/item/MM_2024_36_2_a7/
LA  - ru
ID  - MM_2024_36_2_a7
ER  - 
%0 Journal Article
%A A. V. Gorobets
%A S. A. Soukov
%A A. R. Magomedov
%T Heterogeneous parallel implementation of a multigrid method with full approximation in the  NOISETTE code
%J Matematičeskoe modelirovanie
%D 2024
%P 129-146
%V 36
%N 2
%I mathdoc
%U http://geodesic.mathdoc.fr/item/MM_2024_36_2_a7/
%G ru
%F MM_2024_36_2_a7
A. V. Gorobets; S. A. Soukov; A. R. Magomedov. Heterogeneous parallel implementation of a multigrid method with full approximation in the  NOISETTE code. Matematičeskoe modelirovanie, Tome 36 (2024) no. 2, pp. 129-146. http://geodesic.mathdoc.fr/item/MM_2024_36_2_a7/

[1] K. N. Volkov, Yu. N. Deryugin, V. N. Emelyanov, A. G. Karpenko, A. S. Kozelkov, I. V. Teterina, Metody uskoreniia gazodinamicheskikh raschetov na nestrukturirovannykh setkakh, Fizmatlit, M., 2014

[2] R. P. Fedorenko, “A relaxation method for solving elliptic difference equations”, USSR Comput. Math. Math. Phys., 1 (1961), 1092 | DOI | MR | Zbl

[3] V. S. Akimov, D. P. Silaev, A. S. Simonov, A. S. Semenov, “Issledovanie masshtabiruemosti Flow Vision na klastere s interkonnektom Angara”, Vychislitelnye metody i programmirovanie, 18:4 (2017), 406–415

[4] A. A. Golubev, Yu. N. Deryugin, D. K. Zelenskii, A. S. Kozelkov, S. V. Lashkin, D. P. Silaev, A. S. Simonov, “Paket program Logos. Algebraicheskii mnogosetochnyi metod resheniia SLAU dlia zadach gidrodinamiki”, Sovremennye problem nauki i obrazovaniia, 2013, no. 6

[5] A. S. Kozelkov, S. V. Lashkin, A. A. Kurkin et al, “An Efficient Parallel Implementation of the SIMPLE Algorithm Based on a Multigrid Method”, Numer. Analys. Appl., 13 (2020), 1–16 | DOI | MR | Zbl

[6] N. M. Evstigneev, O. I. Ryabkov, K. M. Gerke, “Stationary Stokes solver for single-phase flow in porous media: A blastingly fast solution based on Algebraic Multigrid Method using GPU”, Advances in Water Resources, 171 (2023), 104340 | DOI

[7] V. T. Zhukov, O. B. Feodoritova, “Multigrid for finite-element discretizations of the equations of aerodynamics”, Math. Models Comput. Simul., 3:4 (2011), 446–456 | DOI | MR | Zbl

[8] D. Demidov, “AMGCL: An efficient, flexible, and extensible algebraic multigrid implementation”, Lobachevskii Journal of Mathematics, 40:5 (2019), 535–546 | DOI | MR | Zbl

[9] B. Krasnopolsky, A. Medvedev, “XAMG: A library for solving linear systems with multiple right-hand side vectors”, SoftwareX, 14 (2021), 100695 | DOI

[10] A.V. Wolkov, “Application of the multigrid approach for solving 3D Navier-Stokes equations on hexahedral grids using the discontinuous Galerkin method”, Comput. Math. Math. Phys., 50:3 (2010), 495–508 | DOI | MR | Zbl

[11] A. V. Gorobets, “An approach to the implementation of the multigrid method with full approximation for CFD problems”, Comput. Math. Math. Phys., 63:11 (2023), 2150–2161 | DOI | MR

[12] A. Gorobets, P. Bakhvalov, “Heterogeneous CPU+GPU parallelization for high-accuracy scale-resolving simulations of compressible turbulent flows on hybrid supercomputers”, Computer Physics Communications, 271 (2022), 108231 | DOI | MR | Zbl

[13] P. A. Bakhvalov, T. K. Kozubskaya, P. V. Rodionov, “EBR schemes with curvilinear reconstructions for hybrid meshes”, Computers Fluids, 239 (2022), 105352 | DOI | MR | Zbl

[14] P. Bakhvalov, T. Kozubskaya, “EBR-WENO scheme for solving gas dynamics problems with discontinuities on unstructured meshes”, Computers Fluids, 157 (2017), 312–324 | DOI | MR | Zbl

[15] P. A. Bakhvalov, M. D. Surnachev, “Method of averaged element splittings for diffusion terms discretization in vertex-centered framework”, Journal of Computational Physics, 450 (2022), 110819 | DOI | MR

[16] H. A. Van der Vorst, “Bi-CGSTAB: A Fast and Smoothly Converging Variant of Bi-CG for the Solution of Nonsymmetric Linear Systems”, SIAM Journal on Scientific Computing, 13 (1992), 631–644 | DOI | MR

[17] D. J. Mavriplis, Multigrid Techniques for Unstructured Meshes, NASA-CR-195070, Von Karman Institute Lecture Series 1995-02, NASA Langley Research Center. Institute for Computer Applications in Science and Engineering, 1995

[18] R. A. Zagitov, S. D. Salnikov, N. V. Shuvalov, “Automatic block-structured grid generation in turbo machine blade passages by turbor software”, Mathematical Models and Computer Simulations, 16 (2024) | DOI

[19] A. Duben, A. Gorobets, S. Soukov, O. Marakueva, N. Shuvaev, R. Zagitov, “Supercomputer Simulations of Turbomachinery Problems with Higher Accuracy on Unstructured Meshes”, RuSCDays 2022, Lecture Notes in Computer Science, 13708, 356–367 | DOI