N-Body Simulations on GPUs

by: Erich Elsen, V Vishal, Mike Houston, Vijay Pande, Pat Hanrahan, Eric Darve

(20 Jun 2007)

View FullText article

arXiv (abstract), arXiv (PDF)

Reviews [Write a review of this article]

There are no reviews of this article

Find related articles from these CiteULike users

ansobol, cwr

Find related articles with these CiteULike tags

distributed, gpgpu, gpu, group, lagrangian, numerical, parallel

Abstract

Commercial graphics processors (GPUs) have high compute capacity at very low cost, which makes them attractive for general purpose scientific computing. In this paper we show how graphics processors can be used for N-body simulations to obtain improvements in performance over current generation CPUs. We have developed a highly optimized algorithm for performing the O(N^2) force calculations that constitute the major part of stellar and molecular dynamics simulations. In some of the calculations, we achieve sustained performance of nearly 100 GFlops on an ATI X1900XTX. The performance on GPUs is comparable to specialized processors such as GRAPE-6A and MDGRAPE-3, but at a fraction of the cost. Furthermore, the wide availability of GPUs has significant implications for cluster computing and distributed computing efforts like Folding@Home.

@misc{citeulike:1422429, abstract = {Commercial graphics processors (GPUs) have high compute capacity at very low cost, which makes them attractive for general purpose scientific computing. In this paper we show how graphics processors can be used for N-body simulations to obtain improvements in performance over current generation CPUs. We have developed a highly optimized algorithm for performing the O(N^2) force calculations that constitute the major part of stellar and molecular dynamics simulations. In some of the calculations, we achieve sustained performance of nearly 100 GFlops on an ATI X1900XTX. The performance on GPUs is comparable to specialized processors such as GRAPE-6A and MDGRAPE-3, but at a fraction of the cost. Furthermore, the wide availability of GPUs has significant implications for cluster computing and distributed computing efforts like Folding@Home.}, author = {Elsen, Erich and Vishal, V. and Houston, Mike and Pande, Vijay and Hanrahan, Pat and Darve, Eric }, citeulike-article-id = {1422429}, eprint = {0706.3060}, keywords = {distributed, gpgpu, group, lagrangian, parallel}, month = {Jun}, posted-at = {2008-07-06 00:36:38}, priority = {2}, title = {N-Body Simulations on GPUs}, url = {http://arxiv.org/abs/0706.3060}, year = {2007} }

RIS record

TY - ELEC ID - citeulike:1422429 L3 - citeulike-article-id:1422429 TI - N-Body Simulations on GPUs N2 - Commercial graphics processors (GPUs) have high compute capacity at very low cost, which makes them attractive for general purpose scientific computing. In this paper we show how graphics processors can be used for N-body simulations to obtain improvements in performance over current generation CPUs. We have developed a highly optimized algorithm for performing the O(N^2) force calculations that constitute the major part of stellar and molecular dynamics simulations. In some of the calculations, we achieve sustained performance of nearly 100 GFlops on an ATI X1900XTX. The performance on GPUs is comparable to specialized processors such as GRAPE-6A and MDGRAPE-3, but at a fraction of the cost. Furthermore, the wide availability of GPUs has significant implications for cluster computing and distributed computing efforts like Folding@Home. KW - distributed KW - gpgpu KW - group KW - lagrangian KW - parallel AU - Elsen, Erich AU - Vishal, V AU - Houston, Mike AU - Pande, Vijay AU - Hanrahan, Pat AU - Darve, Eric PY - 2007/Jun/20/ UR - http://arxiv.org/abs/0706.3060 ER -

RIS BibTeX