FLUPS -- a flexible and performant massively parallel Fourier transform library

TL;DR

This paper enhances the flups library for massively parallel Fourier transforms by adding support for node-centered data layouts and multiple communication strategies, improving flexibility and performance for large-scale scientific computations.

Contribution

The work extends the flups library to support node-centered data and introduces three communication approaches, making it more flexible and suitable for diverse computational scenarios.

Findings

Validated against analytical solutions for various domain types.

Compared performance with accFFT on periodic cases.

Achieved scalable performance up to 49,152 cores.

Abstract

Massively parallel Fourier transforms are widely used in computational sciences, and specifically in computational fluid dynamics which involves unbounded Poisson problems. In practice the latter is usually the most time-consuming operation due to its inescapable all-to-all communication pattern. The original flups library tackles that issue with an implementation of the distributed Fourier transform tailor-made for successive resolutions of unbounded Poisson problems. However the proposed implementation lacks of flexibility as it only supports cell-centered data layout and features a plain communication strategy. This work extends the library along two directions. First, flups implementation is generalized to support a node-centered data layout. Second, three distinct approaches are provided to handle the communications: one all-to-all, and two non-blocking implementations relying on manual packing and MPI_Datatype to communicate over the network. The proposed software is validated against analytical solutions for unbounded, semi-unbounded, and periodic domains. The performance of the approaches is then compared against accFFT, another distributed FFT implementation, using a periodic case. Finally the performance metrics of each implementation are analyzed and detailed on various top-tier European facilities up to 49,152 cores. This work brings flups up to a fully production-ready and performant distributed FFT library, featuring all the possible types of FFTs and with flexibility in the data-layout. The code is available under a BSD-3 license at github.com/vortexlab-uclouvain/flups.