WOLFRAM

Wolfram Language & System Documentation Center

CUDAFourier[cuvec]

finds the discrete Fourier transform of a CUDA vector cuvec.

CUDAFourier[cumat]

finds the discrete Fourier transform of a CUDA matrix cumat.

CUDAFourier[list]

finds the discrete Fourier transform of a list of complex numbers.

Details and Options
Details and Options Details and Options
Examples  
Basic Examples  
Neat Examples  
See Also
Tech Notes
Related Guides
Cite this Page
CUDALink`
CUDALink`

CUDAFourier

CUDAFourier[cuvec]

finds the discrete Fourier transform of a CUDA vector cuvec.

CUDAFourier[cumat]

finds the discrete Fourier transform of a CUDA matrix cumat.

CUDAFourier[list]

finds the discrete Fourier transform of a list of complex numbers.

Details and Options

  • The CUDALink application must be loaded using Needs["CUDALink`"].
  • CUDAFourier works on one-, two-, and three-dimensional lists.

Examples

open all close all

Basic Examples  (4)

First, load the CUDALink application:

Wolfram Language code: Needs["CUDALink`"]

This computes the one-dimensional Fourier transform using CUDA:

Wolfram Language code: res = CUDAFourier[CUDAVector[{1, 0, 1, 1, 0, 1, 1, 1, 0, 1, 1, 1, 1}]];

The result agrees with the Wolfram Language:

Wolfram Language code: Normal[Normal[res]] == Fourier[{1, 0, 1, 1, 0, 1, 1, 1, 0, 1, 1, 1, 1}]

CUDAFourier works on two-dimensional datasets. Here, a dataset is generated:

Wolfram Language code: data = CUDAMatrix[Table[Mod[Binomial[i, j], 2], {i, 0, 63}, {j, 0, 63}]];

Find the logarithmic power spectrum:

Wolfram Language code: ArrayPlot[Log[Abs[Normal@Normal@CUDAFourier[data]]]]

CUDAFourier can be used on multidimensional datasets. This gets the data from an image:

Wolfram Language code: lst = ImageData[[image]];

This performs the Fourier operation:

Wolfram Language code: out = CUDAFourier[lst];

This shows the absolute value of the result:

Wolfram Language code: Image[Abs[out]]

Neat Examples  (1)

Find the Fourier transform of the rule 30 cellular automaton pattern:

Wolfram Language code: ArrayPlot[CellularAutomaton[30, {{1}, 0}, 50]]
Wolfram Language code: [image]

Logarithmic power spectrum:

Wolfram Language code: cudata = CUDAMatrix[CellularAutomaton[30, {{1}, 0}, 50], "Real64"]; ArrayPlot[Log[Abs[Normal@Normal@CUDAFourier[cudata]]]]
Wolfram Research (2010), CUDAFourier, Wolfram Language function, https://reference.wolfram.com/language/CUDALink/ref/CUDAFourier.html.

Text

Wolfram Research (2010), CUDAFourier, Wolfram Language function, https://reference.wolfram.com/language/CUDALink/ref/CUDAFourier.html.

CMS

Wolfram Language. 2010. "CUDAFourier." Wolfram Language & System Documentation Center. Wolfram Research. https://reference.wolfram.com/language/CUDALink/ref/CUDAFourier.html.

APA

Wolfram Language. (2010). CUDAFourier. Wolfram Language & System Documentation Center. Retrieved from https://reference.wolfram.com/language/CUDALink/ref/CUDAFourier.html

BibTeX

@misc{reference.wolfram_2026_cudafourier, author="Wolfram Research", title="{CUDAFourier}", year="2010", howpublished="\url{https://reference.wolfram.com/language/CUDALink/ref/CUDAFourier.html}", note=[Accessed: 13-June-2026]}

BibLaTeX

@online{reference.wolfram_2026_cudafourier, organization={Wolfram Research}, title={CUDAFourier}, year={2010}, url={https://reference.wolfram.com/language/CUDALink/ref/CUDAFourier.html}, note=[Accessed: 13-June-2026]}