PFFT: An Extension of FFTW to Massively Parallel Architectures

We present an MPI based software library for computing fast Fourier transforms (FFTs) on massively parallel, distributed memory architectures based on the Message Passing Interface standard (MPI). Similar to established transpose FFT algorithms, we propose a parallel FFT framework that is based on a...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:SIAM journal on scientific computing Jg. 35; H. 3; S. C213 - C236
1. Verfasser: Pippig, Michael
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Philadelphia Society for Industrial and Applied Mathematics 01.01.2013
Schlagworte:
Algorithms
Architecture
Computation
Computer programs
Decomposition
Distributed memory
Fourier transforms
Libraries
Multidimensional data
Software
ISSN:1064-8275, 1095-7197
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:We present an MPI based software library for computing fast Fourier transforms (FFTs) on massively parallel, distributed memory architectures based on the Message Passing Interface standard (MPI). Similar to established transpose FFT algorithms, we propose a parallel FFT framework that is based on a combination of local FFTs, local data permutations, and global data transpositions. This framework can be generalized to arbitrary multidimensional data and process meshes. All performance-relevant building blocks can be implemented with the help of the FFTW software library. Therefore, our library offers great flexibility and portable performance. Similarly to FFTW, we are able to compute FFTs of complex data, real data, and even- or odd-symmetric real data. All the transforms can be performed completely in place. Furthermore, we propose an algorithm to calculate pruned FFTs more efficiently on distributed memory architectures. For example, we provide performance measurements of FFTs of sizes between $512^3$ and $8192^3$ up to $262144$ cores on a BlueGene/P architecture, up to $32768$ cores on a BlueGene/Q architecture, and up to $4096$ cores on the Julich Research on Petaflop Architectures (JuRoPA). [PUBLICATION ABSTRACT]
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ObjectType-Article-2
ObjectType-Feature-1
content type line 23
ISSN:1064-8275
1095-7197
DOI:10.1137/120885887