A Performance Study of the 2D Ising Model on GPUs

Joshua Romero, Mauro Bisson, Massimiliano Fatica, Massimo Bernaschi
6/14/2019
cs.DC

Official code: NVIDIA/ising-gpu (85 stars, MIT, last commit 2025-03-26).

Abstract

The simulation of the two-dimensional Ising model is used as a benchmark to show the computational capabilities of Graphic Processing Units (GPUs). The rich programming environment now available on GPUs and flexible hardware capabilities allowed us to quickly experiment with several implementation ideas: a simple stencil-based algorithm, recasting the stencil operations into matrix multiplies to take advantage of Tensor Cores available on NVIDIA GPUs, and a highly optimized multi-spin coding approach. Using the managed memory API available in CUDA allows for simple and efficient distribution of these implementations across a multi-GPU NVIDIA DGX-2 server. We show that even a basic GPU implementation can outperform current results published on TPUs and that the optimized multi-GPU implementation can simulate very large lattices faster than custom FPGA solutions.

View on arXivView PDF

Code Implementations(1)

NVIDIA/ising-gpuOfficial100%
MIT

GPU-accelerated Monte Carlo simulations of 2D Ising Model

8533C, CudaJun 13, 20191 years agoMIT

Similar Papers

Design and Analysis of an Extreme-Scale, High-Performance, and Modular Agent-Based Simulation Platform

79% match2025

A differentiable programming framework for spin models

78% match2023

cellGPU: massively parallel simulations of dynamic vertex models

77% match2017

OISMA: On-the-fly In-memory Stochastic Multiplication Architecture for Matrix-Multiplication Workloads

76% match2025

Habitat 2.0: Training Home Assistants to Rearrange their Habitat

76% match1 repo3.2k2021

Adaptive parallelization of multi-agent simulations with localized dynamics

75% match2023

Cite this paper

@article{romero2019performance,
  title  = {A Performance Study of the 2D Ising Model on GPUs},
  author = {Joshua Romero and Mauro Bisson and Massimiliano Fatica and Massimo Bernaschi},
  year   = {2019},
  eprint = {1906.06297},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1906.06297}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/1906.06297.svg)](https://codeofpaper.com/paper/1906.06297)

Discussion