The parallel computing algorithm for a nonhydrostatic model on one or multiple Graphic Processing Units （GPUs） for the simulation of internal solitary waves is presented and discussed. The computational efficiency of the GPU scheme is analyzed by a series of numerical experiments, including an ideal case and the field scale simulations, performed on the workstation and the super- computer system. The calculated results show that the speedup of the developed GPU-based parallel computing scheme, compared to the implementation on a single CPU core, increases with the number of computational grid cells, and the speedup can increase quasi- linearly with respect to the number of involved GPUs for the problem with relatively large number of grid cells within 32 GPUs.
