nrf_dsp_quantize_f32_to_i8()

void nrf_dsp_quantize_f32_to_i8	(	const flt32_t *	p_input,
		int8_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 INT8 vector.

Scaling and Overflow Behavior:

The function uses saturating arithmetic. Results outside of the allowable INT8 range [0x80 0x7F] will be 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 INT8 output vector
[in]	num	Number of samples in input and output vector