Issues of parallel software development for the domain decomposition methods


  • Y.L. Gurieva
  • D.V. Perevozkin


domain decomposition method
parallel algorithm
data structures
numerical experiment


Various aspects of parallel software development for the domain decomposition methods are considered: the application of MPI programming technology for cluster systems, the choice points in the design of parallel programs for the domain decomposition methods, the need to implement a matrix action without its explicit representation, the work with index sets in the software implementation of restriction and continuation operators as well as in the data exchange between subdomains. On a series of numerical experiments for a model problem, the questions of the best choice of the configuration of launching an executable program on a cluster are studied to minimize the computation time and a strategy for performing such experiments is proposed.





Section 1. Numerical methods and applications

Author Biographies

Y.L. Gurieva

D.V. Perevozkin


  1. D. S. Butyugin, Y. L. Guryeva, V. P. Il’in, et al., “Parallel Algebraic Solvers Library Krylov,” Vestn. South Ural Univ. Ser. Vychisl. Mat. Inf. 2 (3), 92-105 (2013).
  2. Y. Saad, Iterative Methods for Sparse Linear Systems (SIAM, Philadelphia, 2003; Mosk. Gos. Univ., Moscow, 2013).
  3. Y. Saad, “A Flexible Inner-Outer Preconditioned GMRES Algorithm,” SIAM J. Sci. Comput. 14 (2), 461-469 (1993).
  4. Y. L. Gurieva, V. P. Il’in, and D. V. Perevozkin, “Algebraic-Geometric and Information Structures of Domain Decomposition Methods,” Vychisl. Metody Programm. 17, 132-146 (2016).
  5. MPI Forum. . Cited May 22, 2018.
  6. Message Passing Interface (MPI). . Cited May 22, 2018.
  7. S. Pissanetzky, Sparse Matrix Technology (Academic, London, 1984; Mir, Moscow, 1988).
  8. X.-C. Cai, C. Farhat, and M. Sarkis, “A Minimum Overlap Restricted Additive Schwarz Preconditioner and Applications in 3D Flow Simulations,” Contemp. Math. 218, 479-485 (1998).
  9. X.-C. Cai and M. Sarkis, “A Restricted Additive Schwarz Preconditioner for General Sparse Linear Systems,” SIAM J. Sci. Comput. 21 (2), 792-797 (1999).
  10. Intel Parallel Programming Professional (Introduction).
  11. V. D. Korneev, Parallel Programming with MPI (Inst. Comput. Math. Math. Geophys., Novosibirsk, 2002) [in Russian].
  12. Biconjugate Gradient Method. . Cited May 22, 2018.
  13. L. Giraud and R. S. Tuminaro, Algebraic Domain Decomposition Preconditioners , Technical Report ENSEEIHT-IRIT RT/APO/06/07 (Université Paul Sabatier, Toulouse, 2006).
  14. MUMPS: MUltifrontal Massively Parallel sparse direct Solver. . Cited May 22, 2018.
  15. Siberian Supercomputing Center. . Cited May 22, 2018.
  16. Intel Trace Analyzer and Collector. . Cited May 22, 2018.
  17. Intel Math Kernel Library. . Cited May 22, 2018.
  18. S. A. Lebedev, I. B. Meerov, A. V. Sysoev, et al., “Optimization and Application of the MUMPS Package for Solving the Three-Dimensional Stationary Strength Problems on Cluster Systems,” in Proc. Int. Supercomputer Conf., Novorossiysk, Russia, September 23-28, 2013 (Mosk. Gos. Univ., Moscow, 2013), pp. 233-237.