Harvesting graphics power for MD simulations

2007/09/20 by J. A. van Meel, Jacobus A. van Meel, A. Arnold +7 · 3 citations
Computer Science · Physics and Astronomy · #Algorithms and Data Compression #Chaos-based Image/Signal Encryption #Parallel Computing and Optimization Techniques #cond-mat.other #cond-mat.soft

paper · pdf · doi:10.1080/08927020701744295

published as Mol. Sim. 34, p259 - 266, 2008 · 12 pages, 5 figures. Submitted to Mol. Sim

arxiv created 2007/09/20 · openalex publication_date 2008/03/01 · arxiv updated 2009/12/01 · openalex created_date 2020/11/23 · openalex updated_date 2026/08/04

Abstract

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 107 flops/.

Cited by

• High performance direct gravitational N-body simulations on graphics processing units II: An implementation in CUDA
• Highly accelerated simulations of glassy dynamics using GPUs: Caveats on limited floating-point precision
• Simulating spin models on GPU
• OpenMM: A Hardware-Independent Framework for Molecular Simulations

Related

• Highly accelerated simulations of glassy dynamics using GPUs: Caveats on limited floating-point precision
• General-purpose molecular dynamics simulations on GPU-based clusters
• N-Body Simulations on GPUs
• Accelerating molecular dynamic simulation on graphics processing units
• Molecular Dynamics Simulation of Macromolecules Using Graphics Processing Unit