Performance potential for simulating spin models on GPU

Abstract

Graphics processing units (GPUs) are recently being used to an increasing degree for general computational purposes. This development is motivated by their theoretical peak performance, which significantly exceeds that of broadly available CPUs. For practical purposes, however, it is far from clear how much of this theoretical performance can be realized in actual scientific applications. As is discussed here for the case of studying classical spin models of statistical mechanics by Monte Carlo simulations, only an explicit tailoring of the involved algorithms to the specific architecture under consideration allows to harvest the computational power of GPU systems. A number of examples, ranging from Metropolis simulations of ferromagnetic Ising models, over continuous Heisenberg and disordered spin-glass systems to parallel-tempering simulations are discussed. Significant speed-ups by factors of up to 1000 compared to serial CPU code as well as previous GPU implementations are observed.

28 pages, 15 figures, 2 tables, version as published

References in corpus (11)

• Feedback-optimized parallel tempering Monte Carlo
• Harvesting graphics power for MD simulations
• Multi-GPU Accelerated Multi-Spin Monte Carlo Simulations of the 2D Ising Model
• Make life simple: unleash the full power of the parallel tempering algorithm
• Performance potential for simulating spin models on GPU
• Simulating spin models on GPU
• The critical behavior of 3D Ising glass models: universality and scaling corrections
• Connected component identification and cluster update on GPU
• Simulating Lattice Spin Models on Graphics Processing Units
• Speeding up parallel tempering simulations
• The Heisenberg spin glass model on GPU: myths and actual facts

Cited by in corpus (32)

• Performance potential for simulating spin models on GPU
• Random number generators for massively parallel simulations on GPU
• Simulating spin models on GPU
• GPU accelerated population annealing algorithm
• Solid--liquid transition of skyrmions in a two-dimensional chiral magnet
• q-State Potts model metastability study using optimized GPU-based Monte Carlo algorithms
• A Performance Study of the 2D Ising Model on GPUs
• Connected component identification and cluster update on GPU
• Massively parallel multicanonical simulations
• Parallel Tempering Simulation of the three-dimensional Edwards-Anderson Model with Compact Asynchronous Multispin Coding on GPU
• GPU accelerated Monte Carlo simulations of lattice spin models
• Ageing of the 2+1 dimensional Kardar-Parisi-Zhang model
• Optimized GPU simulation of continuous-spin glass models
• Highly optimized simulations on single- and multi-GPU systems of 3D Ising spin glass
• Ageing at the Spin-Glass/Ferromagnet Transition: Monte Carlo Simulation using GPUs
• Adaptive Multi-GPU Exchange Monte Carlo for the 3D Random Field Ising Model
• Universal behavior of crystalline membranes: crumpling transition and Poisson ratio of the flat phase
• Simulation of 1+1 dimensional surface growth and lattices gases using GPUs
• Dynamic scaling in the 2D Ising spin glass with Gaussian couplings
• Comparison of Different Parallel Implementations of the 2+1-Dimensional KPZ Model and the 3-Dimensional KMC Model
• GPU Based Parallel Ising Computing for Combinatorial Optimization Problems in VLSI Physical Design
• GPU parallel simulation algorithm of Brownian particles with excluded volume using Delaunay triangulations
• Gibbs Markov Random Fields with Continuous Values based on the Modified Planar Rotator Model
• Accurate Sampling with Noisy Forces from Approximate Computing
• Multipath Metropolis Simulation of Classical Heisenberg Model
• Suppressing correlations in massively parallel simulations of lattice models
• Superdiffusion-like behavior in zero-temperature coarsening of the $d=3$ Ising model
• Dynamical heterogeneities as fingerprints of a backbone structure in Potts models
• GPU-based simulation of the long-range Potts model via parallel tempering
• Massively parallel simulations for disordered systems
• Massive-Scale Simulations of 2D Ising and Blume-Capel Models on Rack-Scale Multi-GPU Systems
• GPU-based Ising Computing for Solving Balanced Min-Cut Graph Partitioning Problem