cunumeric.fft.rfft2#

cunumeric.fft.rfft2(a: ndarray, s: Sequence[int] | None = None, axes: Sequence[int] = (-2, -1), norm: str | None = None) → ndarray#

Compute the 2-dimensional FFT of a real array.

Parameters:

a (array) – Input array, taken to be real.
s (sequence of ints, optional) – Shape of the FFT.
axes (sequence of ints, optional) – Axes over which to compute the FFT.
norm ({"backward", "ortho", "forward"}, optional) – Normalization mode (see numpy.fft). Default is “backward”. Indicates which direction of the forward/backward pair of transforms is scaled and with what normalization factor.

Returns:

out – The result of the real 2-D FFT.

Return type:

ndarray

Notes

This is really rfftn with different defaults. For more details see rfftn. Multi-GPU usage is limited to data parallel axis-wise batching.