Multi-GPU fast Fourier transforms in MATLAB (for large-scale phase-field crystal simulations)
It addresses memory and speed bottlenecks in large-scale pseudo-spectral simulations for materials science researchers using phase-field crystal models.
This paper presents a MATLAB-based framework for multi-GPU fast Fourier transforms, achieving approximately sixfold speedup for standard phase-field crystal simulations and up to sixtyfold for multiphysics extensions compared to CPU-based implementations on hundreds of cores.
We present a MATLAB-based framework for two- and three-dimensional fast Fourier transforms on multiple GPUs for large-scale numerical simulations using the pseudo-spectral Fourier method. The software implements two complementary multi-GPU strategies that overcome single-GPU memory limitations and accelerate spectral solvers. This approach is motivated by and applied to phase-field crystal (PFC) models, which are governed by tenth-order partial differential equations, require fine spatial resolution, and are typically formulated in periodic domains. Our resulting numerical framework achieves significant speedups, approximately sixfold for standard PFC simulations and up to sixtyfold for multiphysics extensions, compared to a purely CPU-based implementation running on hundreds of cores.