The Simulation and Implementation of Discrete Particle System based on CUDA

Author

Qiang-qiang, Huang ; Shun-liang, Jiang ; Xu Shao-ping ; Tian-wen, Dong

Author_Institution

Sch. of Inf. Engineereing, Nanchang Univ., Nanchang, China

fYear

2011

fDate

29-31 July 2011

Firstpage

501

Lastpage

504

Abstract

In this paper, NVIDIA´s parallel computing architecture CUDA is used to implement a discrete particle simulation system. In the neighbor search part, an algorithm based on hash list is used. In the collision part, the stream of CUDA is used to split one step simulation to four parallel streams, the asynchronous copy method is used to output, then an efficient way to use the CUDA memory model is designed. The results shown that the CUDA´s discrete particle system is efficient and effective.

Keywords

computer graphic equipment; coprocessors; file organisation; parallel architectures; parallel memories; reproduction (copying); CUDA memory model; NVIDIA; asynchronous copy method; discrete particle simulation system; hash list; parallel computing architecture; parallel stream; Computational modeling; Force; Graphics processing unit; Instruction sets; Kernel; Parallel processing; Solids; CUDA; DEM; GPU; Parallel Programing; Particle System; Stream;

fLanguage

English

Publisher

ieee

Conference_Titel

Business Computing and Global Informatization (BCGIN), 2011 International Conference on

Conference_Location

Shanghai

Print_ISBN

978-1-4577-0788-9

Electronic_ISBN

978-0-7695-4464-9

Type

conf

DOI

10.1109/BCGIn.2011.132

Filename

6003959