A Performance Study of the 2D Ising Model on GPUs
arXiv:1906.06297 · doi:10.1016/j.cpc.2020.107473
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.
References in corpus (4)
Cited by in corpus (12)
- Roadmap for Unconventional Computing with Nanotechnology
- CMOS + stochastic nanomagnets: heterogeneous computers for probabilistic inference and learning
- Double-Free-Layer Stochastic Magnetic Tunnel Junctions with Synthetic Antiferromagnets
- Exploring instantons with spin-lattice systems
- Deep learning of phase transitions with minimal examples
- A geometrical interpretation of critical exponents
- Dynamical phase transitions in model: a Monte Carlo and mean-field theory study
- Universal exotic dynamics in critical mesoscopic systems: Simulating the square root of Avogadro's number of spins
- Quantum Integer Programming (QuIP) 47-779: Lecture Notes
- A differentiable programming framework for spin models
- Massive-Scale Simulations of 2D Ising and Blume-Capel Models on Rack-Scale Multi-GPU Systems
- Simulating magnetic antiskyrmions on the lattice