Title :
Accelerate Smoothed Particle Hydrodynamics using GPU
Author :
Gao, Xiaopeng ; Wang, Zhiqiang ; Wan, Han ; Long, Xiang
Author_Institution :
State Key Lab. of Virtual Reality Technol. & Syst., Beihang Univ., Beijing, China
Abstract :
Physic-based fluid simulation is used extensively nowadays; however the traditional serial algorithm can´t satisfy the real-time requirement due to its complexity and computeintensive. The development of modern GPU makes this possible. In this paper, a Smoothed Particle Hydrodynamics (SPH) method for incompressible fluid was implemented using CUDA on GPU. Since the algorithm was executed on the GPU entirely, the method can take full advantage of massive computational power of modern graphics hardware. The experiment results show that our GPU based SPH implementation can achieve the rate of 89 frames per second in the simulation of 102K particles and gain nearly 140× speedups compared with the serial algorithm.
Keywords :
computer graphics; coprocessors; flow simulation; physics computing; CUDA; GPU; fluid simulation; graphics hardware; incompressible fluid; smoothed particle hydrodynamics; Computational modeling; Fluids; Force; Graphics processing unit; Indexes; Instruction sets; Kernel; CUDA; GPU; Smoothed Particle Hydrodynamics; acceleration; fluid simulation;
Conference_Titel :
Information Computing and Telecommunications (YC-ICT), 2010 IEEE Youth Conference on
Conference_Location :
Beijing
Print_ISBN :
978-1-4244-8883-4
DOI :
10.1109/YCICT.2010.5713129