High performance implementations of the 2D Ising model on GPUs

DOI10.1016/J.CPC.2020.107473MaRDI QIDQ6040137zbMATH OpenOpenAlexFDO

Authors Joshua Romero, Mauro Bisson, Massimiliano Fatica, M. Bernaschi

Publication date 24 May 2023

Published in Computer Physics Communications (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1906.06297

zbMATH Keywords

GPU programmingIsing modelsoftware including parallel algorithmsstatistical physics and thermodynamics

Mathematics Subject Classification ID

Numerical algorithms for specific classes of architectures (65Y10) Lattice systems (Ising, dimer, Potts, etc.) and systems on graphs arising in equilibrium statistical mechanics (82B20)

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.

Recommendations

• Multi-GPU accelerated multi-spin Monte Carlo simulations of the 2D Ising model
• GPU accelerated Monte Carlo simulation of the 2D and 3D Ising model
• GPU-based single-cluster algorithm for the simulation of the Ising model
• Performance potential for simulating spin models on GPU
• Benchmarking GPU and CPU codes for Heisenberg spin glass over-relaxation

Cites work

• Crystal Statistics. I. A Two-Dimensional Model with an Order-Disorder Transition
• Equation of state calculations by fast computing machines
• GPU accelerated Monte Carlo simulation of the 2D and 3D Ising model
• scientific article; zbMATH DE number 1753846 (Why is no real title available?)
• Multi-GPU accelerated multi-spin Monte Carlo simulations of the 2D Ising model
• Multi-spin coding: A very efficient technique for Monte Carlo simulations of spin systems
• Performance potential for simulating spin models on GPU

Cited in

(6)

• Benchmarking GPU and CPU codes for Heisenberg spin glass over-relaxation
• GPU-acceleration of tensor renormalization with pytorch using CUDA
• The QISG suite: high-performance codes for studying quantum Ising spin glasses
• Critical Ising system testing of high-quality random number generators
• An enumeration decomposition algorithm for solving the Ising model
• Ascend to Science: Exploration of AI Chips for Scientific Computing

This page was built for publication: High performance implementations of the 2D Ising model on GPUs

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6040137)