耗散粒子动力学图像处理器并行运算的实现

GPU-accelerated dissipative particle dynamics simulations

计算机模拟的时空尺度限制了它的进一步应用和发展,而高性能图像处理器(GPU)得以充分利用的现实将会使计算机模拟突破该限制。为此使用图像处理器实现耗散粒子动力学(DPD)模拟方法的并行运算。通过模拟结果发现图像处理器的并行运算将会大幅度提高计算效率。为了检验自编的代码,研究了并行运算模拟中压力和体系密度的关系,二元共混体中Flory-Huggins参数、保守力参数和链长之间的关系,模拟结果和以前的报道一致。

Due to the limitation of spatial and temporal scales, computer simulations have significant barriers to their further applications and developments. However, computer simulations would break through the limitations because the further acceleration is possible through the advanced computer hardware of Graphic Processing Units （GPU）, which is the high performance computer processor designed to accelerate graphical applications. In this study, dissipative particle dynamics simulation was accelerated by GPUs. The simulation results show that a single GPU can give performance competitive with a much more expensive CPU cluster. To verify the GPU-accelerated code, the relation of pressure and destiny, and of the Flory- Huggins parameter, the parameter of the conservative force and polymer length in the simulations were discussed and compared with the previous publications.