Harvesting graphics power for MD simulations

被引：133

作者：

van Meel, J. A. ^{[1
]}

Arnold, A. ^{[1
]}

Frenkel, D. ^{[2
]}

Zwart, S. F. Portegies ^{[3
,4
]}

Belleman, R. G. ^{[4
]}

机构：

[1] FOM Inst Atom & Mol Phys, Amsterdam, Netherlands

[2] Univ Cambridge, Dept Chem, Cambridge CB2 1EW, England

[3] Univ Amsterdam, Astron Inst Anton Pannekoek, Amsterdam, Netherlands

[4] Univ Amsterdam, Sect Computat Sci, Amsterdam, Netherlands

来源：

MOLECULAR SIMULATION | 2008年 / 34卷 / 03期

关键词：

molecular dynamics simulation; GPGPU; random number generator;

D O I：

10.1080/08927020701744295

中图分类号：

O64 [物理化学（理论化学）、化学物理学];

学科分类号：

070304 ; 081704 ;

摘要：

We discuss an implementation of molecular dynamics (MD) simulations on a graphic processing unit (GPU) in the NVIDIA CUDA language. We tested our code on a modern GPU, the NVIDIA GeForce 8800 GTX. Results for two MD algorithms suitable for short-ranged and long-ranged interactions, and a congruential shift random number generator are presented. The performance of the GPU's is compared to their main processor counterpart. We achieve speedups of up to 40, 80 and 150 fold, respectively. With the latest generation of GPU's one can run standard MD simulations at 10(7) flops/$.

引用

页码：259 / 266

页数：8

共 20 条

[1]

ANDERSON JA, 2007, UNPUB J COMPUT

[2]

[Anonymous], 1998, SCI SIMULATIONS SPEC

[3]

[Anonymous], P ACM SIGGRAPH EUROG

[4]

BELLEMAN RG, 2007, IN PRESS NEW ASTRON

[5] OpenMP: An industry standard API for shared-memory programming [J].

Dagum, L ;

Menon, R .

IEEE COMPUTATIONAL SCIENCE & ENGINEERING, 1998, 5 (01) :46-55

[6]

Fernando R, 2003, CG TUTORIAL DEFINITI

[7]

Frenkel D., 2000, Computational Science Series

[8]

Gabriel E, 2004, LECT NOTES COMPUT SC, V3241, P97

[9]

*LAMMPS, 2005, BENCHM LAMMPS MOL DY

[10]

Larsen E.S., 2001, SC '01: Proc. ACM/IEEE Conference on Supercomputing, P55

← 1 2 →