Particle Simulation Using Serial,GPU and Distributed Approaches
Xiaoqian Men, Dennis K. Peters · Memorial University Research Repository (Memorial University) · 2013
In computer engineering, simulation is a popular and reasonable method to study scientific problems, which evaluates the motion of different objects in various sizes of simulation spaces. In order to achieve better performance, different approaches will be applied. Nowadays, both GPU and cluster show great power in parallel computing. In this thesis, a particle simulation is formulated by following the motion of interacting particles as they move in some constrained space, colliding with each other and the walls. We compare three solutions to this problem: i) using traditional (serial) computing, ii) using general purpose computing on a graphics processing card (GPGPU), and iii) using a distributed cluster architecture and the message passing interface (MPI). Based on the experimental data gathered from the tests, the performance of the algorithms is analyzed to show how the speedup varies across different architectures and with the number of compute cores used.