基于CUDA的大规模群体行为实时仿真并行实现及优化

群体仿真中个体从环境中查找相关对象时会导致较高的时间复杂度。要使大规模群体能够实时仿真,必须降低模型运算的时间复杂度或者提高计算平台的能力。通过对Biods模型为典型案例进行研究,提出一种基于统一计算架构(CUDA)的大规模群体行为实时仿真并行实现及优化的方法。实现中将个体与GPU逻辑线程一一对应,通过将仿真环境离散化来提高相关个体查找的效率,通过并行化基数排序法将个体信息组织成具有空间局部性的数组,提高图形处理器(GPU)内存带宽的利用率。通过实验验证了该方法将仿真个体的数量提升到CPU方法的约7.3倍。

Parallel simulation and optimization of CUDA-based real-time huge crowd behavior

That the individuals search relevant objects from the environment may cause high time complexity during the crowd simulation.If the crowd should be simulated in real-time,the time complexity of the model needs reducing and the computing capability of the simulation platform needs enhancing.In this paper,the Biods model was studied as a typical case and a solution of how to parallelize and optimize the real-time huge crowd simulation based on Compute Unified Device Architecture(CUDA) was presented.Each individual was correspondent to a logical Graphic Processing Unit(GPU) thread.By discretizing simulation environment,the efficiency of searching the relevant individuals was improved.The individual information was organized into an array with the spatial locality by parallel radix sort in order to improve the utilization of the GPU memory bandwidth.The experiment verifies the solution presented here has improved number of simulation individuals up to about 7.3 times as CPU solution.