nrf_dsp_cfft_radix8by4_f32()

void nrf_dsp_cfft_radix8by4_f32	(	const nrf_dsp_cfft_f32_t *	p_cfft,
		flt32_t *	p_input )

#include <include/nrf_edgeai/dsp/transform/fft/nrf_dsp_fft_f32.h>

The floating-point complex FFT uses a mixed-radix algorithm. Multiple radix-4 stages are performed along with a radix-1 stage, as needed. The algorithm supports lengths of [32, 256, 2048] and each length uses a different twiddle factor table.

Parameters

[in]	p_cfft	Pointer to instance of complex FFT structure nrf_dsp_cfft_f32_t
[in,out]	p_input	Pointer to buffer with input samples, the FFT doing in place and will modify input buffer with FFT results. The results will be written to input array in the interleaved fashion: {real[0], imag[0], real[1], imag[1], ...}