cuFINUFFT: a load-balanced GPU library for general-purpose nonuniform FFTs

arXiv2102.08463MaRDI QIDQ6360809

Alex H. Barnett, Garrett Wright, Joakim Andén, Johannes Blaschke, Yu-hsuan Shih

Publication date: 16 February 2021

Abstract: Nonuniform fast Fourier transforms dominate the computational cost in many applications including image reconstruction and signal processing. We thus present a general-purpose GPU-based CUDA library for type 1 (nonuniform to uniform) and type 2 (uniform to nonuniform) transforms in dimensions 2 and 3, in single or double precision. It achieves high performance for a given user-requested accuracy, regardless of the distribution of nonuniform points, via cache-aware point reordering, and load-balanced blocked spreading in shared memory. At low accuracies, this gives on-GPU throughputs around $10^9$ nonuniform points per second, and (even including host-device transfer) is typically 4-10$imes$ faster than the latest parallel CPU code FINUFFT (at 28 threads). It is competitive with two established GPU codes, being up to 90$imes$ faster at high accuracy and/or type 1 clustered point distributions. Finally we demonstrate a 5-12$imes$ speedup versus CPU in an X-ray diffraction 3D iterative reconstruction task at $10^{-12}$ accuracy, observing excellent multi-GPU weak scaling up to one rank per GPU.

Has companion code repository: https://github.com/flatironinstitute/finufft

This page was built for publication: cuFINUFFT: a load-balanced GPU library for general-purpose nonuniform FFTs

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6360809)