This article is cited in 5 scientific papers (total in 5 papers)
Parallel partitioning tool GridSpiderPar for large mesh decomposition
E. N. Golovchenko, M. V. Iakobovski
Keldysh Institute of Applied Mathematics of Russian Academy of Sciences, Moscow
The problem of load balancing arises in parallel mesh-based numerical solution of problems of continuum mechanics, energetics, electrodynamics etc. on high-performance computing systems. The number of processors to run a computational problem is often unknown. It makes sense, therefore, to partition a mesh into a great number of microdomains which then are used to create subdomains. Graph partitioning methods implemented in state-of-the-art parallel partitioning tools ParMETIS, Jostle, PT-Scotch and Zoltan are based on multilevel algorithms. That approach has a shortcoming of forming unconnected subdomains. Another shortcoming of present graph partitioning methods is generation of strongly imbalanced partitions. The program package for parallel large mesh decomposition GridSpiderPar was developed. We compared different partitions into microdomains, microdomain graph partitions and partitions into subdomains of several meshes ($10^8$ vertices, $10^9$ elements) obtained by means of the partitioning tool GridSpiderPar and the packages ParMETIS, Zoltan and PT-Scotch. Balance of the partitions, edge-cut and number of unconnected subdomains in different partitions were compared as well as the computational performance of gas-dynamic problem simulations run on different partitions. The obtained results demonstrate advantages of the devised algorithms.
parallel programming, graph partitioning, mesh decomposition.
PDF file (1076 kB)
E. N. Golovchenko, M. V. Iakobovski, “Parallel partitioning tool GridSpiderPar for large mesh decomposition”, Num. Meth. Prog., 16:4 (2015), 507–517
Citation in format AMSBIB
\by E.~N.~Golovchenko, M.~V.~Iakobovski
\paper Parallel partitioning tool GridSpiderPar for large mesh decomposition
\jour Num. Meth. Prog.
Citing articles on Google Scholar:
Related articles on Google Scholar:
This publication is cited in the following articles:
S. A. Sukov, “Biblioteka preprotsessornoi obrabotki nestrukturirovannykh setok hm4PreprocessorLib”, Preprinty IPM im. M. V. Keldysha, 2016, 108, 20 pp.
S. A. Sukov, “Metod szhatiya topologii gibridnykh setok i biblioteka podprogramm hm4PackLib”, Preprinty IPM im. M. V. Keldysha, 2017, 128, 15 pp.
B. N. Chetverushkin, V. P. Osipov, V. I. Baluta, “Podkhody k modelirovaniyu posledstvii prinyatiya reshenii v usloviyakh protivodeistviya”, Preprinty IPM im. M. V. Keldysha, 2018, 043, 15 pp.
E. N. Golovchenko, “Obzor algoritmov dekompozitsii grafov”, Preprinty IPM im. M. V. Keldysha, 2020, 002, 38 pp.
E. N. Golovchenko, M. V. Yakobovskii, V. A. Balashov, E. B. Savenkov, “Sravnenie algoritmov dekompozitsii oblasti v zadache pryamogo modelirovaniya techeniya zhidkosti v porovom prostranstve obraztsov gornykh porod”, Matem. modelirovanie, 32:4 (2020), 107–115
|Number of views:|