Harvesting graphics power for MD simulations

TL;DR

This paper presents an implementation of molecular dynamics simulations on NVIDIA GPUs, achieving significant speedups over traditional CPU computations, enabling faster and more efficient MD simulations.

Contribution

The paper introduces a GPU-based MD simulation implementation using CUDA, demonstrating substantial performance improvements over CPU versions.

Findings

Speedups of up to 80x for short-range interactions

Speedups of up to 40x for long-range interactions

Speedups of up to 150x for random number generation

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 80, 40 and 150 fold, respectively. With newest generation of GPU's one can run standard MD simulations at 10^7 flops/$.