float16.h File Reference

Half-Precision Floating-Point (fp16) Definitions. More...

#include <stdint.h>
#include <stdlib.h>
#include <float.h>

Include dependency graph for float16.h:

This graph shows which files directly or indirectly include this file:

Go to the source code of this file.

Data Structures
union	float_uint32_union_t

Typedefs
typedef uint16_t	float16_t

Functions
static float	as_f32 (float16_t h)
static float16_t	as_f16 (float f)

Detailed Description

Half-Precision Floating-Point (fp16) Definitions.

This header file provides a unified interface for half-precision floating-point numbers. It includes support for half-precision floating-point numbers on systems that do not natively support them.

The half-precision floating-point number is represented using a 16-bit unsigned integer. The conversion functions between half-precision and single-precision floating-point numbers are provided.