Geodesic
Dynamic load balancing with the parallel partitioning tool GridSpiderPar
Matematičeskoe modelirovanie, Tome 34 (2022) no. 4, pp. 59-69.

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

Dynamically adaptive meshes are used often in high-performance computing. A mesh is locally refined or de-refined in spots of interest or where high gradients of an objective function arise. Its repartitioning is needed periodically to balance the load on the processors. Dynamic load balancing algorithms were developed on the base of the parallel geometric algorithm of mesh partitioning and the parallel incremental algorithm of graph partitioning from the partitioning tool GridSpiderPar. Initial partition of a mesh with local refinement (6.7$\cdot$10$^6$ hexahedrons) was compared with the results of repartitioning using the devised algorithms. Comparison results show advantages of the parallel geometric algorithm on this mesh and features of the parallel incremental algorithm application.
Keywords: high-performance computing, graph partitioning, mesh decomposition. 
@article{MM_2022_34_4_a3,
     author = {E. N. Golovchenko},
     title = {Dynamic load balancing with the parallel partitioning tool {GridSpiderPar}},
     journal = {Matemati\v{c}eskoe modelirovanie},
     pages = {59--69},
     publisher = {mathdoc},
     volume = {34},
     number = {4},
     year = {2022},
     language = {ru},
     url = {http://geodesic.mathdoc.fr/item/MM_2022_34_4_a3/}
}
TY  - JOUR
AU  - E. N. Golovchenko
TI  - Dynamic load balancing with the parallel partitioning tool GridSpiderPar
JO  - Matematičeskoe modelirovanie
PY  - 2022
SP  - 59
EP  - 69
VL  - 34
IS  - 4
PB  - mathdoc
UR  - http://geodesic.mathdoc.fr/item/MM_2022_34_4_a3/
LA  - ru
ID  - MM_2022_34_4_a3
ER  - 
%0 Journal Article
%A E. N. Golovchenko
%T Dynamic load balancing with the parallel partitioning tool GridSpiderPar
%J Matematičeskoe modelirovanie
%D 2022
%P 59-69
%V 34
%N 4
%I mathdoc
%U http://geodesic.mathdoc.fr/item/MM_2022_34_4_a3/
%G ru
%F MM_2022_34_4_a3
E. N. Golovchenko. Dynamic load balancing with the parallel partitioning tool GridSpiderPar. Matematičeskoe modelirovanie, Tome 34 (2022) no. 4, pp. 59-69. http://geodesic.mathdoc.fr/item/MM_2022_34_4_a3/

[1] K. Schloegel, G. Karypis, V. Kumar, “A Unified Algorithm for Load-balancing Adaptive Scientific Simulations”, SC '00: Proceedings of the 2000 ACM/IEEE Conference on Supercomputing, 59 | DOI

[2] K. Schloegel, G. Karypis, V. Kumar, “Wavefront Diffusion and LMSR: Algorithms for Dynamic Repartitioning of Adaptive Meshes”, Transactions on parallel and distributed systems, 12:5, may (2001)

[3] C. Walshaw, M. Cross, M. G. Everett, Parallel dynamic graph-partitioning for unstructured meshes, Mathematics Research Report 97/IM/20, Centre for Numerical Modelling and Process Analysis, University of Greenwich, March 27, 1997, 10 pp. | MR

[4] U. V. Catalyurek, E. G. Boman, K. D. Devine, D. Bozda, R. Heaphy, L. A. Riesen, “Hypergraph-based Dynamic Load Balancing for Adaptive Scientific Computations”, 2007 IEEE International Parallel and Distributed Processing Symposium, 1–11 | DOI

[5] U. V. Catalyurek, C. Aykanat, “Hypergraph-partitioning based decomposition for parallel sparse-matrix vector multiplication”, IEEE Transactions on Parallel and Distributed Systems, 10:7 (1999), 673–693 | DOI

[6] B. Hendrickson, T. G. Kolda, “Graph partitioning models for parallel computing”, Parallel Computing, 26 (2000), 1519–1534 | DOI | MR | Zbl

[7] E. N. Golovchenko, M. A. Kornilina, M. V. Yakobovskiy, “Algorithms in the parallel partitioning tool GridSpiderPar for large mesh decomposition”, Proc. of the 3rd Inter. Conf. on Exascale Applications and Software, EASC 2015, University of Edinburgh, 2015, 120–125

[8] E. N. Golovchenko, M. V. Iakobovskii, “Paket parallelnoi dekompozitsii bolshikh setok GridSpiderPar”, Vychislitelnye metody i programmirovanie, 16 (2015), 507–517

[9] E. N. Golovchenko, Dekompozitsiia raschetnyh setok dlia resheniia zadach mehaniki sploshnyh sred na vysokoproizvoditelnyh vychislitelnyh sistemah, dissert. ... kand. fiz.-mat. nauk, IPM im. M.V. Keldysha RAN, M., 2014