RUS  ENG
Full version
JOURNALS // Numerical methods and programming // Archive

Num. Meth. Prog., 2013 Volume 14, Issue 3, Pages 334–342 (Mi vmp120)

This article is cited in 2 papers

Вычислительные методы и приложения

Implementation of parallel calculations on graphics processor units in the LOGOS computational fluid dynamics package

K. N. Volkova, Yu. N. Deryuginb, V. N. Emelyanova, A. G. Karpenkoc, A. S. Kozelkovb, P. G. Smirnova, I. V. Teterinaa

a Baltic State Technical University "Voenmech"
b Federal State Unitary Enterprise "Russian Federal Nuclear Center — All-Russian Research Institute of Experimental Physics", Sarov, Nizhny Novgorod region
c St. Petersburg State University, Department of Mathematics and Mechanics

Abstract: A number of tools for the numerical simulation of three-dimensional flows of viscous compressible gas with the use of graphics processor units are developed. The finite volume method implemented in the LOGOS package is used to solve the Navier-Stokes equations on unstructured meshes. Different methods for the flux calculations through faces of finite volumes and features of implementation of a turbulence model are considered. The CUDA technology is used to implement parallel numerical algorithms. The solutions to some benchmark problems of internal and external gas dynamics are discussed. The speed-up of calculations performed on graphics processor units compared to the calculations performed on the corresponding central processor unit is analyzed.

Keywords: graphics processor unit; parallel algorithm; gas dynamics; finite volume method; unstructured mesh; CUDA technology; LOGOS package.

UDC: 532.529

Received: 14.05.2013



© Steklov Math. Inst. of RAS, 2024