Parallel Fast Multipole Method accelerated FFT on HPC clusters

With increasing sizes of distributed systems, there comes an increased risk of communication bottlenecks. In the past decade there has been a growing interest in communication-avoiding algorithms. The distributed memory Fast Fourier Transform is an important algorithm which suffers from major commun...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Parallel computing Ročník 104-105; s. 102783
Hlavní autori: Mehta, Chahak, Karthi, Amarnath, Jetly, Vishrut, Chaudhury, Bhaskar
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Elsevier B.V 01.07.2021
Predmet:
Beowulf cluster
Communication avoiding algorithms
Fast Fourier Transform
Fast Multipole Method
High performance computing
Parallel programming
Fast Fourier Transform
Fast Multipole Method
Parallel programming
Communication avoiding algorithms
High performance computing
Beowulf cluster
ISSN:0167-8191, 1872-7336
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:With increasing sizes of distributed systems, there comes an increased risk of communication bottlenecks. In the past decade there has been a growing interest in communication-avoiding algorithms. The distributed memory Fast Fourier Transform is an important algorithm which suffers from major communication bottlenecks. In this work, we take a look at an existing communication-avoiding algorithm FMM-FFT, an alternative to FFT which utilizes the Fast Multipole Method (FMM) to reduce communications to a single all-to-all communication. We present a detailed implementation of FMM-FFT relying on modern libraries and demonstrate it on two distinct distributed memory architectures notably a traditional Intel Xeon based HPC cluster and then a Beowulf cluster. We show that while the FMM-FFT is significantly slower than FFT on the traditional HPC cluster, on the Beowulf cluster it outperforms standard FFT, consistently getting speedups of 1.5x or more against FFTW. We then proceed to show how the communication to computation cost metric is important and useful in explaining the performance results of FMM-FFT against standard FFT. The source code pertaining to this work is being made publicly available under a permissive open source licence at Github.
ISSN:0167-8191
1872-7336
DOI:10.1016/j.parco.2021.102783