Geodesic
Load balancing method for heterogeneous CFD algorithms
Žurnal Srednevolžskogo matematičeskogo obŝestva, Tome 23 (2021) no. 2, pp. 193-206.

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

The problem of load balancing for unstructured heterogeneous numerical algorithms for simulation of physical processes is considered. A computational distribution method for hybrid supercomputers with multicore CPUs and massively parallel accelerators is described. The load balancing procedure includes determination of dual graph vertices and edges weights, devices’ performance test and two-level decomposition of the computational mesh based on domain decomposition method. First level decomposition involves the graph partitioning between supercomputer nodes. On the second level node subdomains are partitioned between the MPI-processes running on the nodes. The details of the proposed approach are considered on the example of an unstructured finite-volume algorithm for modeling the Navier-Stokes equations with polynomial reconstruction of variables and explicit time integration scheme. The parallel version of the algorithm is developed using the MPI, OpenMP and CUDA programming models. The parameters of performance, parallel efficiency and scalability of the heterogeneous program are given. The results mentioned are obtained during the simulation of a supersonic flow around a sphere on a mixed mesh consisting of tetrahedrons, triangular prisms, quadrangular pyramids and hexagons. 
@article{SVMO_2021_23_2_a4,
     author = {S. A. Sukov},
     title = {Load balancing method for heterogeneous {CFD} algorithms},
     journal = {\v{Z}urnal Srednevol\v{z}skogo matemati\v{c}eskogo ob\^{s}estva},
     pages = {193--206},
     publisher = {mathdoc},
     volume = {23},
     number = {2},
     year = {2021},
     language = {ru},
     url = {http://geodesic.mathdoc.fr/item/SVMO_2021_23_2_a4/}
}
TY  - JOUR
AU  - S. A. Sukov
TI  - Load balancing method for heterogeneous CFD algorithms
JO  - Žurnal Srednevolžskogo matematičeskogo obŝestva
PY  - 2021
SP  - 193
EP  - 206
VL  - 23
IS  - 2
PB  - mathdoc
UR  - http://geodesic.mathdoc.fr/item/SVMO_2021_23_2_a4/
LA  - ru
ID  - SVMO_2021_23_2_a4
ER  - 
%0 Journal Article
%A S. A. Sukov
%T Load balancing method for heterogeneous CFD algorithms
%J Žurnal Srednevolžskogo matematičeskogo obŝestva
%D 2021
%P 193-206
%V 23
%N 2
%I mathdoc
%U http://geodesic.mathdoc.fr/item/SVMO_2021_23_2_a4/
%G ru
%F SVMO_2021_23_2_a4
S. A. Sukov. Load balancing method for heterogeneous CFD algorithms. Žurnal Srednevolžskogo matematičeskogo obŝestva, Tome 23 (2021) no. 2, pp. 193-206. http://geodesic.mathdoc.fr/item/SVMO_2021_23_2_a4/

[1] M-S. Liou, K-H. Kao, Progress in Grid Generation: From Chimera to DRAGON Grids, National Aeronautics and Space Adminstration Publ., Cleveland, 1994, 26 pp.

[2] P. Zaspel, M. Griebel, “Solving incompressible two-phase flows on multi-GPU clusters”, Computers and Fluids, 80 (2013), 356–364 | DOI | MR | Zbl

[3] A. A. Davydov, B. N. Chetverushkin, E. V. Shilnikov, “Simulating flows of incompressible and weakly compressible fluids on multicore hybrid computer systems”, Comput. Math. and Math. Phys., 50 (2010), 2157–2165 | DOI | MR | Zbl

[4] M. M. Krasnov, P. A. Kuchugov, M. E. Ladonkina, V. F. Tishkin, “Discontinuous Galerkin method on three-dimensional tetrahedral grids: Using the operator programming method”, Math. Models Comput. Simul., 9:5 (2017), 529–543 | DOI | MR

[5] A. Gorobets, S. Soukov, P. Bogdanov, “Multilevel parallelization for simulating turbulent flows on most kinds of hybrid supercomputers”, Computers and Fluids, 173 (2018), 171–177 | DOI | MR | Zbl

[6] K. Schloegel, G. Karypis, V. Kumar, “Parallel multilevel algorithms for multiconstraint graph partitioning”, Euro-Par 2000 Parallel Processing, eds. A. Bode, T. Ludwig, W. Karl, R. Wismuller, Springer, Berlin-Heidelberg, 2000, 296–310 | DOI

[7] E. N. Golovchenko, M. A. Kornilina, M. V. Yakobovskiy, “Algorithms in the parallel parti-tioning tool GridSpiderPar for large mesh decomposition”, Proceedings of the 3rd Inter-national Conference on Exascale Applications and Software (EASC 2015), University of Edinburgh, 2015, 120–125

[8] J. Blazek, Computational Fluid Dynamics: Principles and Applications, Elsevier, Amsterdam, 2001, 470 pp. | MR | Zbl

[9] S. Kim, D. Caraeni, B. Makarov, “A Multidimensional Linear Reconstruction Scheme for Arbitrary Unstructured Grids”, Technical report., AIAA 16th Computational Fluid Dynamics Conference (Orlando, Florida American Institute of Aeronautics and Astronautics. June 2003), 2003 | DOI

[10] S. A. Soukov, A. V. Gorobets, P. B. Bogdanov, “Modeling Compressible Flows on All Existing Hybrid Supercomputers”, Math. Models Comput. Simul., 10 (2018), 135–144 | DOI | MR

[11] T. Nagata, T. Nonomura, S. Takahashi, Y. Mizuno, K. Fukuda, “Investigation on subsonic to supersonic flow around a sphere at low Reynolds number of between 50 and 300 by direct numerical simulation”, Physics of Fluids, 28 (2016), 056101-1–056101-20 | DOI | MR