A new CUDA-based GPU implementation of the two-dimensional Athena code

• Autorzy: Wasilijew A. , Murawski K.
• Języki publikacji: EN

Abstrakty

EN

We present a new version of the Athena code, which solves magnetohydrodynamic equations in two-dimensional space. This new implementation, which we have named Athena-GPU, uses CUDA architecture to allow the code execution on Graphical Processor Unit (GPU). The Athena-GPU code is an unofficial, modified version of the Athena code which was originally designed for Central Processor Unit (CPU) architecture. We perform numerical tests based on the original Athena-CPU code and its GPU counterpart to make a performance analysis, which includes execution time, precision differences and accuracy. We narrowed our tests and analysis only to double precision floating point operations and two-dimensional test cases. Our comparison shows that results are similar for both two versions of the code, which confirms correctness of our CUDA-based implementation. Our tests reveal that the Athena-GPU code can be 2 to 15-times faster than the Athena-CPU code, depending on test cases, the size of a problem and hardware configuration.

Słowa kluczowe

EN

CUDA-based GPU implementation; two-dimensional Athena code; magnetohydrodynamic equations

• Wydawca: Polska Akademia Nauk, Wydział IV Nauk Technicznych
• Czasopismo: Bulletin of the Polish Academy of Sciences. Technical Sciences
• Rocznik: 2013
• Tom: Vol. 61, nr 1
• Strony: 239--250
• Opis fizyczny: Bibliogr. 20 poz., rys., tab.

Twórcy

autor

Wasilijew A.

autor

Murawski K.

• Faculty of Physics, Mathematics and Informatics, University of Maria Curie-Skłodowska, 1 M. Curie-Skłodowskiej Sq., 20-031 Lublin, Poland

Bibliografia

• [1] K. Murawski and T. Tanaka, “Godunov-type methods for twocomponent magnetohydrodynamic equations”, Bull. Pol. Ac.:Tech. 60 (2), 343-348 (2012).
• [2] http://www.astro.princeton.edu/~jstone/zeus.html (2011).
• [3] http://flash.uchicago.edu/website/home (2011).
• [4] http://plutocode.ph.unito.it/ (2011).
• [5] http://nirvana-code.aip.de/ (2011).
• [6] http://folk.uio.no/mcmurry/amhd/ (2011).
• [7] https://trac.princeton.edu/Athena (2011).
• [8] http://www.mcs.anl.gov/research/projects/mpi (2011).
• [9] NVIDIA, NVIDIA CUDA Programming Guide 3.1, NVIDIA (2010).
• [10] H. Schive, Y. Tsai, and T. Chiueh, “GAMER: a graphic processing unit accelerated adaptive-mesh-refinement code for astrophysics”, Astrophys. J. Suppl. 186, 457-484 (2010).
• [11] B. Pang, U. Pen, and M. Perrone, “Magnetohydrodynamics on Heterogeneous architectures: a performance comparison”, CoRR, abs/1004.1680 (2010).
• [12] H.-C. Wong, U.-H. Wong, X. Feng, and Z. Tang, “Efficient magnetohydrodynamic simulations on graphics processing units with CUDA”, eprint arXiv:0908.4362 (2009).
• [13] J.M. Stone, T.A. Gardiner, P. Teuben, J.F. Hawley, and J.B. Simon, “Athena: a new code for astrophysical MHD”, Astrophys. J. Suppl. 178 (1), 137-177 (2008).
• [14] T.A. Gardiner and J.M. Stone, “An unsplit Godunov method for ideal MHD via constrained transport”, J. Comp. Phys. 205 (2), 509-539 (2005).
• [15] K. Murawski, “Numerical solutions of magnetohydrodynamic equations”, Bull. Pol. Ac.: Tech. 59 (1), 1-8 (2011).
• [16] P. Colella and P.R. Woodward, “The Piecewise Parabolic Method (PPM) for gas-dynamical simulations”, J. Comp. Phys. 54 (1), 174-201 (1984).
• [17] P.L. Roe, “Approximate Riemann solvers, parameter vectors, and difference schemes”, J. Comp. Phys. 43 (2), 357-372 (1981).
• [18] B. Einfeldt, C.D. Munz, P.L. Roe, and B. Sjogreen, “On Godunov-type methods near low densities”, J. Comput. Phys. 92 (2), 273-295 (1991).
• [19] NVIDIA, Whitepaper. NVIDIA Next Generation CUDA ComputeArchitecture: Fermi, NVIDIA (2009).
• [20] K. Murawski, K. Murawski Jr., and H.-Y. Schive, “Numerical simulations of acoustic waves with the graphic acceleration GAMER code”, Bull. Pol. Ac.: Tech. 60 (4), 787-792 (2012).