mindscience.sciops.fft.asd_irfft

mindscience.sciops.fft.asd_irfft(*args, **kwargs)[source]

1D complex-to-real inverse FFT transform using Ascend NPU acceleration.

This function performs 1D Inverse Real Fast Fourier Transform on complex input tensors, optimized for Ascend NPU hardware acceleration.

Parameters

  • *args –

    Variable length argument list. Typically includes:

    • xr (Tensor): Real part of input complex tensor with data type float32.

    • xi (Tensor): Imaginary part of input complex tensor with data type float32.

  • **kwargs – Arbitrary keyword arguments.

Returns

Tensor. Output real tensor with data type float32.

Raises

ValueError – If input tensor data type is not float32.

Examples

>>> import mindspore as ms
>>> from mindscience.sciops.fft import asd_irfft
>>> xr = ms.Tensor([[1.0, 2.0, 3.0]], ms.float32)
>>> xi = ms.Tensor([[0.0, 0.0, 0.0]], ms.float32)
>>> yr = asd_irfft(xr, xi)
>>> print(yr.shape)
(1, 4)