Abstract
A parallel computation technology for modeling fluid dynamics problems by finite-volume and finite-difference methods of high accuracy is presented. The development of an algorithm, the design of a software implementation, and the creation of parallel programs for computations on large-scale computing systems are considered. The presented parallel technology is based on a multilevel parallel model combining various types of parallelism: with shared and distributed memory and with multiple and single instruction streams to multiple data flows.
Similar content being viewed by others
References
A. Ramirez, “The Mont-Blanc architecture,” International Supercomputing Conference, Hamburg, Germany, June 17–21, 2012 (Hamburg, 2012).
V. V. Voevodin and Vl. V. Voevodin, Parallel Computations (BKhV-Peterburg, St. Petersburg, 2002) [in Russian].
A. Grama, G. Karypis, V. Kumar, and A. Gupta, Introduction to Parallel Computing, 2nd ed. (Addison-Wesley, Reading, MA, 2003).
Yu. B. Vasilevskii, I. N. Kon’shin, G. V. Kopytov, and K. M. Terekhov, INMOST: Program Platform and Graphic Environment for Development of Parallel Numerical Models on General Grids (Mosk. Gos. Univ., Moscow, 2013) [in Russian].
R. Aubry, G. Houzeaux, M. Vazquez, and J. M. Cela, “Some useful strategies for unstructured edge-based solvers on shared memory machines,” Int. J. Numerical Meth. Eng. 85, 537–561 (2010).
P. B. Bogdanov, A. A. Efremov, A. V. Gorobets, and S. A. Sukov, “Application of a scheduler for efficient data exchange on hybrid supercomputers with massively parallel accelerators,” Vychisl. Metody Program. 14, 122–134 (2013).
MPI: A Message-Passing Interface Standard, Version 3.0, Message Passing Interface, Forum, September 21, 2012 (http://www.mpi-forum.org/docs/mpi-3.0/mpi30-report.pdf).
OpenMP Application Program Interface, Version 4.0, July 2013 (http://www.openmp.org/mp-documents/OpenMP4.0.0.pdf).
P. Bogdanov and A. A. Efremov, “Programming infrastructure of heterogeneous computing based on OpenCL and its applications,” GPU Technology Conference GTC-2013, San Jose, USA, March 18–21, 2013 (San Jose, CA, 2013).
P. B. Bogdanov, A. V. Gorobets, and S. A. Sukov, “Adaptation and optimization of basic operations for an unstructured mesh CFD algorithm for computation on massively parallel accelerators,” Comput. Math. Math. Phys. 53(8), 1383–1394 (2013).
T. Barth, “Numerical methods for conservation laws on structured and unstructured meshes,” VKI for Fluid Dynamics, VKI Lectures series (2003), Vol. 5.
I. V. Abalakin and T. K. Kozubskaya, “A scheme based on edge-oriented quasi-1D reconstruction of variables for solving aerodynamics and aeroacoustics problems on unstructured meshes,” Mat. Model. 25(8), 109–136 (2013).
P. A. Bakhvalov, “Quasi-one-dimensional reconstruction scheme on convex polygonal meshes for solving aeroacoustics problems,” Mat. Model. 25, 95–108 (2013).
A. Gorobets, F. X. Trias, and A. Oliva, “A parallel MPI + OpenMP + OpenCL algorithm for hybrid supercomputations of incompressible flows,” Comput. Fluids 88, 764–772 (2013).
M. Soria, C. D. Perez-Segarra, and A. Oliva, “A direct parallel algorithm for the efficient solution of the pressure-correction equation of incompressible flow problems using loosely coupled computers,” Numer. Heat Transfer Part B 41, 117–138 (2002).
K. Schloegel, G. Karypis, and V. Kumar, “Parallel static and dynamic multi-constraint graph partitioning,” Concurrency Comput. Practice Experience 14(3), 219–240 (2002).
F. Pellegrini, PT-Scotch and libPTScotch 6.0 User’s Guide, 2012 (https://gforge.iniia.fr/docman/view.php/248/8261/ptscotch-user6.0.pdf).
E. N. Golovchenko, “Parallel software package for large mesh decomposition,” Mat. Model. 23(10), 3–18 (2011).
B. Krasnopolsky, “The reordered BiCGStab method for distributed memory computer systems,” ICCS 2010 Procedia Comput. Sci. 1(1), 213–218 (2010).
A. V. Gorobets, S. A. Sukov, and P. B. Bogdanov, “Toward heterogeneous supercomputing in CFD,” Inf. Tekhnol. Vychisl. Sist., No. 4, 23–34 (2013).
E. Cuthill and J. McKee, “Reducing the bandwidth of sparse symmetric matrices,” Proceedings of the 24th National ACM Conference (1969), pp. 157–172.
A. V. Gorobets, S. A. Sukov, A. O. Zheleznyakov, P. B. Bogdanov, B. N. Chetverushkin, “Application of GPU in hybrid two-level MPI + OpenMP parallelization on heterogeneous computing systems,” Vest. Yuzhno-Ural. Gos. Univ., No. 25 (242), 76–86 (2011).
A. Monakov, A. Lokhmotov, and A. Avetisyan, “Automatically tuning sparse matrix-vector multiplication for GPU architectures,” High Performance Embedded Architectures and Compilers, Lect. Notes Comput. Sci. 5952, 111–125 (2010).
I. V. Abalakin, P. A. Bakhvalov, A. V. Gorobets, A. P. Duben’, T. K. Kozubskaya, “Parallel research code NOISEtte for large-scale CFD and CAA simulations,” Vychisl. Metody Program. 13, 110–125 (2012).
G. Oyarzun, R. Borrell, A. Gorobets, and A. Oliva, “MPI-CUDA sparse matrix-vector multiplication for the conjugate gradient method with an approximate inverse preconditioner,” Comput. Fluids 92, 244–252 (2014).
F. X. Trias, O. Lehmkuhl, A. Oliva, C. D. Pérez-Segarra, R. W. C. P. Verstappen, “Symmetry-preserving discretization of Navier-Stokes equations on collocated unstructured grids,” J. Comput. Phys. 258(1), 246–267 (2014).
R. W. C. P. Verstappen and A. E. P. Veldman, “Symmetry-preserving discretization of turbulent flow,” J. Comput. Phys. 187, 343–368 (2003).
V. Titarev, M. Dumbser, and S. Utyuzhnikov, “Construction and comparison of parallel implicit kinetic solvers in three spatial dimensions,” J. Comput. Phys. 256, 17–33 (2014).
A Guide to Vectorization with Intel C++ Compilers, 2012 (http://download-software.intel.com/sites/default/files/8c/a9/CompilerAutovectorizationGuide.pdf).
Author information
Authors and Affiliations
Corresponding author
Additional information
Original Russian Text © A.V. Gorobets, 2015, published in Zhurnal Vychislitel’noi Matematiki i Matematicheskoi Fiziki, 2015, Vol. 55, No. 4, pp. 641–652.
Rights and permissions
About this article
Cite this article
Gorobets, A.V. Parallel technology for numerical modeling of fluid dynamics problems by high-accuracy algorithms. Comput. Math. and Math. Phys. 55, 638–649 (2015). https://doi.org/10.1134/S0965542515040065
Received:
Published:
Issue Date:
DOI: https://doi.org/10.1134/S0965542515040065