Parallel multilayer particle collision detection method based on performance estimation

Particle collision detection is important for diverse simulating systems that involve spatial interactions between particles. Traditional parallelization strategy, which equally partitions the domain, can lead to skewed load distributions if the particles are not uniformly distributed. Moreover, the communication cost is relatively high when it comes to multilayer collision detection method. To solve this problem and to improve the parallel efficiency, this paper proposes an estimation-based domain decomposition method (ED-method) and an estimation-based multilayer method (EM-method) for homogeneous processors. Based on the performance estimation, the tasks are reassigned when it is necessary to balance the workload among different homogeneous processes. In the experiments, we compare these methods under different simulation conditions. Compared with the traditional method, the proposed method achieves better load balancing by taking advantage of features of the multilayer collision detection, and the results prove the excellence of the proposed method.