https://github.com/juliagpu/clfft.jl

Julia bindings for AMD's clFFT library
https://github.com/juliagpu/clfft.jl

clfft julia opencl

Last synced: about 1 month ago
JSON representation

Julia bindings for AMD's clFFT library

• Host: GitHub
• URL: https://github.com/juliagpu/clfft.jl
• Owner: JuliaGPU
• License: other
• Created: 2013-11-15T23:57:55.000Z (about 11 years ago)
• Default Branch: master
• Last Pushed: 2023-08-22T15:04:39.000Z (about 1 year ago)
• Last Synced: 2024-10-11T14:41:15.467Z (about 1 month ago)
• Topics: clfft, julia, opencl
• Language: Julia
• Homepage:
• Size: 95.7 KB
• Stars: 16
• Watchers: 10
• Forks: 16
• Open Issues: 3
• Metadata Files:
  • Readme: README.md
  • License: LICENSE.md

Awesome Lists containing this project

README

        
# CLFFT.jl

Julia bindings to clFFT library.

## Example

```julia

import OpenCL

import CLFFT

import FFTW

using LinearAlgebra

const cl = OpenCL.cl

const clfft = CLFFT

_, ctx, queue = cl.create_compute_context()

N = 100

X = ones(ComplexF64, N)

bufX = cl.Buffer(ComplexF64, ctx, :copy, hostbuf=X)

p = clfft.Plan(ComplexF64, ctx, size(X))

clfft.set_layout!(p, :interleaved, :interleaved)

clfft.set_result!(p, :inplace)

clfft.bake!(p, queue)

clfft.enqueue_transform(p, :forward, [queue], bufX, nothing)  

result = cl.read(queue, bufX)

@assert isapprox(norm(result - FFTW.fft(X)), zero(Float32))

```