nrf_axon_xty_16_16_32_output_stride()

nrf_axon_result_e nrf_axon_xty_16_16_32_output_stride	(	const int16_t *	x_ptr,
		const int16_t *	y_ptr,
		int32_t *	out_ptr,
		uint16_t	length,
		uint8_t	rounding_bits,
		uint8_t	output_extra_stride,
		nrf_axon_syncmode_blocking_e	block_mode,
		bool	keep_reservation )

vector multiplies 2 16bit vectors to produce a 32bit vector, with option to have unpacked output vector.

Useful for applying a hamming window on real input before performing an FFT, which requires complex input. Pass output_extra_stride=1 and the output will be placed every other word in the real coefficients slots. A separate function would need to be called to 0 out the imaginary coefficients.

If output_extra_stride is not needed it can be set to 0, but using axon_xty_16_16_32() is preferred for better performance. It performs multiplication of 2 16bit vectors and produces a 32bit output. @parameter out_ptr location to place output. Can safely overlap either input @parameter length number of of elements in the input vectors. Maximum value is 512. @rounding_bits number of bits to round the output by. @parameter output_extra_stride Nuumber of output slots to skip between each output value (skipped slots are not modified)