Parallelization of algorithms for solving the Boltzmann equation for GPU-based computations
Khristianovich Institute of Theoretical and Applied Mechanics SB RAS (Russia, Novosibirsk)
AIP Conf. Proc., Volume 1333, pp. 946-951, 27th International Symposium on Rarefied Gas Dynamics, 2011
The paper describes specific features of parallelization of collision integral computation algorithms, which are conditioned by the CUDA architecture of parallelization on graphic cards [1].
November 6, 2011 by hgpu
