MPI-GPU/CUDA implementation of TVDLF method for the two-dimensional advection equation

• Autorzy: Murawski K. , Murawski K. , Stpiczyński P.
• Języki publikacji: EN

Abstrakty

EN

We implement Total Variation Diminishing Lax Friedrichs (TVDLF, or Rusanov) method to obtain numerical solutions of the two-dimensional advection equation. Despite the simplicity of this equation, solving it numerically is a formidable task. Based on the use of the original C++ MPI-GPU/CUDA code we present results of numerical tests we performed. These tests show that our code represents well the square wave profiles, leading to up to 60- times faster calculations with the use of MPI than with its serial counter-part.

Słowa kluczowe

EN

computer science; modelling; numerical methods; hyperbolic equations

• Wydawca: Systems Research Institute, Polish Academy of Sciences
• Czasopismo: Control and Cybernetics
• Rocznik: 2014
• Tom: Vol. 43, no. 2
• Strony: 307--320
• Opis fizyczny: Bibliogr. 13 poz., rys.

Twórcy

autor

Murawski K.

• Institute of Informatics, UMCS, Pl. M. Curie-Sklodowskiej 1, 20-031 Lublin, Poland

autor

Murawski K.

• Faculty of Mathematics, Physics and Informatics, UMCS, ul. Radziszewskiego 10, 20-031 Lublin, Poland

autor

Stpiczyński P.

• Institute of Mathematics, UMCS, Pl. M. Curie-Sklodowskiej 1, 20-031 Lublin, Poland

Bibliografia

• 1. LEIST, A., PLAYNE, D.P., HAWICK, K.A. (2009) Exploiting graphical processing units for data-parallel scientific applications. Concurrency and Computation: Practice and Experience 21, 2400-2437.
• 2. LEVEQUE, R.J. (2002) Finite-volumeMethods for Hyperbolic Problems. Cambridge University Press, Cambridge.
• 3. MORTON, K.W., Mayers, D.F. (2005) Numerical Solution of Partial Differential Equations, An Introduction. Cambridge University Press, Cambridge.
• 4. MURAWSKI, K. (2002) Analytical and Numerical Methods for Wave Propagation in Fluids. World Scientific, Singapore.
• 5. MURAWSKI, K., LEE, D. (2012) Godunov-type algorithms for numerical modeling of solar plasma. Control and Cybernetics 41 (1), 35-56.
• 6. MURAWSKI, K., Jr., MURAWSKI, K., STPICZY´ NSKI, P. (2012) Implementation of MUSCL-Hancock method into the C++ code for the Euler equations. Bull. Pol. Ac.: Tech. 60 (1), 45-53.
• 7. MURAWSKI, K., MURAWSKI, K., Jr., SCHIEVE, H.-Y. (2013) Numerical simulations of acoustic waves with the graphic acceleration GAMER code. Bull. Pol. Ac.: Tech. 60 (4), 787-792.
• 8. NICKOLLS, J., DALLY, W.J. (2010) The GPU Computing Era. IEEE Micro 30, 56-69.
• 9. NICKOLLS, J., BUCK, I., GARLAND, M., SKADRON, K. (2008) Scalable Parallel Programming with CUDA. ACM Queue 6, 40-53.
• 10. SCHIEVE, H.-Y., TSAI, Y., CHIUEH, T. (2010) GAMER: a graphic processing unit accelerated adaptive-mesh refinement code for astrophysics. Astrophys. J. Suppl. 186 (2), 457-484.
• 11. TORO, E. (2009) Riemann Solvers and Numerical Methods for Fluid Dynamics. Springer, Berlin.
• 12. T´OTH, G., ODSTRCIL, D. (1996) Comparison of Some Flux Corrected Transport and Total Variation Diminishing Numerical Schemes for Hydrodynamic and Magnetohydrodynamic Problems. J. Comput. Physics 128 (1), 82-100.
• 13. WASILJEW, A., MURAWSKI, K. (2013) A new CUDA-based GPU implementation of the two-dimensional Athena code. Bull. Pol. Ac.: Tech. 61 (1), 239-250.