Bilinear interpolation algorithm is broadly applied in digital image processing but its calculation speed is very slow. In order to improve its performance in calculation, this paper proposes a graphic processing unit acceleration-based bilinear interpolation parallel It mainly utilizes Wallis transforming independence among various blocks in bilinear interpolation, which is adaptable to characteristics of GPU parallel processing structure. It maps traditional serial bilinear interpolation algorithm to CUDA parallel programming model and optimize thread allocation, memory usage, hardware resources division, etc, to make full use of huge calculation ability. The experiment results show bilinear interpolation parallel algorithm can greatly improve calculation speed with increasing image resolution.