Multi-GPU Accelerated Multi-Spin Monte Carlo Simulations of the 2D Ising Model

TL;DR

This paper presents a multi-GPU implementation of the 2D Ising model simulation that significantly accelerates computations and enables larger system sizes, demonstrating near-linear scaling with multiple GPUs.

Contribution

It extends existing GPU algorithms to multi-GPU setups, achieving high acceleration and scalability for large-scale 2D Ising model simulations.

Findings

Achieved up to 35x speedup on a single GPU compared to CPU implementations.

Successfully scaled simulations nearly linearly with the number of GPUs.

Accurately reproduced the critical temperature using finite size scaling.

Abstract

A modern graphics processing unit (GPU) is able to perform massively parallel scientific computations at low cost. We extend our implementation of the checkerboard algorithm for the two dimensional Ising model [T. Preis et al., J. Comp. Phys. 228, 4468 (2009)] in order to overcome the memory limitations of a single GPU which enables us to simulate significantly larger systems. Using multi-spin coding techniques, we are able to accelerate simulations on a single GPU by factors up to 35 compared to an optimized single Central Processor Unit (CPU) core implementation which employs multi-spin coding. By combining the Compute Unified Device Architecture (CUDA) with the Message Parsing Interface (MPI) on the CPU level, a single Ising lattice can be updated by a cluster of GPUs in parallel. For large systems, the computation time scales nearly linearly with the number of GPUs used. As proof of concept we reproduce the critical temperature of the 2D Ising model using finite size scaling techniques.