warp.tile_ifft

warp.tile_ifft(

inout: Tile[Vector[Float, Literal[2]], tuple[int, ...]],

) → None

• Kernel: true
• Python: false
• Differentiable: true

Compute the inverse FFT along the last dimension of an N-D tile, in place.

Identical to tile_fft() apart from the sign of the exponent: x[n] = sum_k X[k] * exp(+2*pi*i*k*n/N). The transform is unnormalized – it does not divide by N – so a forward transform followed by an inverse transform multiplies the data by N. inout is overwritten with its inverse transform.

Supported dtypes, tile requirements, backend selection, and the supported transform sizes are the same as for tile_fft(); see it for details and a usage example.

This is a cooperative operation, so every thread in the block must call it.

Parameters:

inout – The tile to transform in place.