Abstract: The solution of multi-GPU parallel computing under virtualization is proposed for the large-scale computing tasks. The multi-threads and flow mode are supported to implement the multi GPU cooperative computing. The multi-level storage structure for GPU, transmission and other aspects are analyzed to accelerate the program. We make experimental verification of representative scientific computing examples such as Monte Carlo method. Experimental results show that with the increase of the calculation scale, it can achieve a speed-up ratio close to the number of GPU.