Namespace ManagedCuda.CudaFFT

Classes

CudaFFTException

An CudaFFTException is thrown, if any wrapped call to the CUFFT-library does not return Success.

CudaFFTNativeMethods

C# wrapper for the NVIDIA CUFFT API (--> cufft.h)

CudaFFTPlan1D

Creates a 1D FFT plan configuration for a specified signal size and data type. The batch input parameter tells CUFFT how many 1D transforms to configure.

Creates a 2D FFT plan configuration according to specified signal sizes and data type. This class is the same as CudaFFTPlan1D except that it takes a second size parameter, ny, and does not support batching.

CudaFFTPlan3D

Creates a 3D FFT plan configuration according to specified signal sizes and data type. This class is the same as CudaFFTPlan2D except that it takes a third size parameter nz.

CudaFFTPlanMany

Creates a FFT plan configuration of dimension rank, with sizes specified in the array n. The batch input parameter tells CUFFT how many transforms to configure in parallel. With this function, batched plans of any dimension may be created.

Input parameters inembed, istride, and idist and output parameters onembed, ostride, and odist will allow setup of noncontiguous input data in a future version (Beta status in version 4.0). Note that for CUFFT 3.0, these parameters are ignored and the layout of batched data must be side‐by‐side and not interleaved.

CudaFFTPlanMany64

Structs

cufftHandle

cufftHandle is a handle type used to store and access CUFFT plans.

Enums

Compatibility

Certain R2C and C2R transforms go much more slowly when FFTW memory layout and behaviour is required. The default is "best performance", which means not-compatible-with-fftw. Use the cufftSetCompatibilityMode(cufftHandle, Compatibility) API to enable exact FFTW-like behaviour.