In this paper, we explore the implementation of fault simulator for small-delay faults on Graphics Processing Unit (GPU). Nowadays the size of integrated circuit is getting smaller and smaller, the clock frequency has become faster and faster, which leads to the effects of small delay fault on chip and is also increasingly obvious. Small delay simulation has become highly important, it is directly related to the accuracy of product and its time to market. At the same time, small delay simulation is a very time consuming process, which requires constantly looking for ways to accelerate the simulation. In recent years, GPU has been used to accelerate the programs of intensive computation in many areas and has achieved very good results. Based on these two points, we consider combining the parallelism of small delay simulation with the high parallel computing ability of GPU to accelerate small delay simulation. Experimental results indicate that our approach is on average 42 when compared to the traditional fault simulation engine.