nrf_dsp_quantize_f32_to_i16()

void nrf_dsp_quantize_f32_to_i16	(	const flt32_t *	p_input,
		int16_t *	p_out,
		uint16_t	num )

#include <include/nrf_edgeai/dsp/support/nrf_dsp_quantization.h>

Quantize the elements of the floating-point vector to INT16 vector.

Scaling and Overflow Behavior

The function uses saturating arithmetic. Results outside of the allowable INT16 range [0x8000 0x7FFF] are saturated.

Note

In order to apply rounding, the library should be rebuilt with the NRF_DSP_USE_MATH_ROUNDING macro

Parameters

[in]	p_input	Points to the floating-point input vector
[out]	p_out	Points to the INT16 output vector
[in]	num	Number of samples in each vector