The Design and Implementation of FFTW3

By Matteo Frigo, Steven G. Johnson. 2005

5,245 citations recorded by the source corpus.

Subfields: Computational Theory and Mathematics, Electrical and Electronic Engineering, Numerical Methods & Scientific Computing, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Theory and Mathematics

In Electrical and Electronic Engineering

In Numerical Methods & Scientific Computing

In Signal Processing

Citations in the corpus

Wav2Letter++: A Fast Open-source Speech Recognition System (2018, methodology): “We use the FFTW library to compute discrete Fourier transforms [8].”
FNet: Mixing Tokens with Fourier Transforms (2021, methodology): “The standard FFT algorithm is the Cooley–Tukey algorithm (Cooley and Tukey, 1965; Frigo and Johnson, 2005), which recursively re-expresses the DFT of a sequence of length N = N1N2 in terms of N1 smaller discrete Fourier transforms of sizes N2 to reduce the computation time to O(N logN).”
A Survey on Homomorphic Encryption Schemes (2017, methodology): “However, in FHEW such performance is achieved using only a few hundred lines of code with the use of one additional library, FFTW [Frigo and Johnson 2005].”
PetaBricks: a language and compiler for algorithmic choice (2009, methodology): “This problem has been addressed for certain speciﬁc algorithms by autotuning software, such as ATLAS (Whaley and Dongarra 1998) and FFTW (Frigo and Johnson 1998, 2005), which have training phases where optimal algorithms and cutoffs are automatically selected.”
Bayesian physical reconstruction of initial conditions from large-scale structure surveys (2012, methodology): “It utilizes the FFTW3 library for Fast Fourier Transforms and the GNU scientific library (gsl) for random number generation (Frigo & Johnson 2005; Galassi et al. 2003).”
Dedalus: A flexible framework for numerical simulations with spectral methods (2019, background): “• The FFTW C-library for fast Fourier transforms [86].”
An efficient simultaneous reconstruction technique for tomographic particle image velocimetry (2009, positive): “based correlation, using the FFTW library (Frigo and Johnson 2005).”
QUANTUM ESPRESSO: a modular and open-source software project for quantum simulations of materials (2009, positive): “ both in serial and in parallel execution. High serial performance across different architectures is achieved by the systematic use of standardized mathematical libraries (BLAS, LAPACK [28], and FFTW [29]) for which highly optimized implementations exist on many platforms; when proprietary optimizat”
Implementing a search for aligned-spin neutron star - black hole systems with advanced ground based gravitational wave detectors (2014, methodology): “At the same time, the inverse FFT is dispatched to the appropriate library (CUFFT [67] for CUDA, FFTW [68] or MKL [69] for CPU) and again is not written by the PyCBC developers.”
Diversitree: comparative phylogenetic analyses of diversification in R (2012, methodology): “…manipulation; the deSolve package (Soetaert, Petzoldt & Setzer 2010) and sundials library (Hindmarsh et al. 2005) are used for solving the systems of diﬀerential equations for the discrete trait models; and fftw (Frigo & Johnson 2005) is used to solve the partial diﬀerential equations in QuaSSE.”
PIVlab – Towards User-friendly, Affordable and Accurate Digital Particle Image Velocimetry in MATLAB (2014, methodology): “The filter evaluates For the FFT calculations, FFTW is used [17] which accepts inputs of arbitrary size, but is slow for sizes that are prime or which have large prime factors (note the peaks in the graph).”