Regular lattice and small-world spin model simulations using CUDA and GPUs

Hawick, K. A.; Leist, A.; Playne, D. P.

Abstract

Data-parallel accelerator devices such as Graphical Processing Units (GPUs) are providing dramatic performance improvements over evenmulti-coreCPUs for lattice-oriented applications in computational physics. Models such as the Ising and Potts models continue to play a role in investigating phase transitions on smallworld and scale-free graph structures. These models are particularly well-suited to the performance gains possible using GPUs and relatively high-level device programming languages such as NVIDIA'sComputeUnified Device Architecture (CUDA).We report on algorithms andCUDAdata-parallel programming techniques for implementingMetropolis Monte Carlo updates for the Isingmodel using bit-packing storage, and adjacency neighbour lists for various graph structures in addition to regular hypercubic lattices. We report on parallel performance gains and also memory and performance tradeoffs using GPU/CPU and algorithmic combinations.

Citation

Hawick, K. A., Leist, A., & Playne, D. P. (2011). Regular lattice and small-world spin model simulations using CUDA and GPUs. International Journal of Parallel Programming, 39(2), 183-201. https://doi.org/10.1007/s10766-010-0143-4

• Journal Article Type: Article
• Online Publication Date: Jul 3, 2010
• Publication Date: Apr 1, 2011
• Deposit Date: Nov 13, 2014
• Journal: International Journal Of Parallel Programming
• Print ISSN: 0885-7458
• Electronic ISSN: 1573-7640
• Publisher: Springer Verlag
• Peer Reviewed: Peer Reviewed
• Volume: 39
• Issue: 2
• Pages: 183-201
• DOI: https://doi.org/10.1007/s10766-010-0143-4
• Keywords: Theoretical Computer Science; Software; Information Systems
• Public URL: https://hull-repository.worktribe.com/output/470713