Simd Library Documentation.

Home | Release Notes | Download | Documentation | Issues | GitHub
Brain Floating Point (16-bit) Numbers

Functions for conversion between BFloat16 (16-bit Brain Floating Point) and 32-bit Floating Point numbers and other. More...

Functions

SIMD_API void SimdFloat32ToBFloat16 (const float *src, size_t size, uint16_t *dst)
 Converts numbers in the array from 32-bit float to 16-bit bfloat format. More...
 
SIMD_API void SimdBFloat16ToFloat32 (const uint16_t *src, size_t size, float *dst)
 Converts numbers in the array from 16-bit bfloat to 32-bit float format. More...
 

Detailed Description

Functions for conversion between BFloat16 (16-bit Brain Floating Point) and 32-bit Floating Point numbers and other.

Function Documentation

◆ SimdFloat32ToBFloat16()

void SimdFloat32ToBFloat16 ( const float *  src,
size_t  size,
uint16_t *  dst 
)

Converts numbers in the array from 32-bit float to 16-bit bfloat format.

Parameters
[in]src- a pointer to the input array with 32-bit float point numbers.
[in]size- a size of input and output array.
[out]dst- a pointer to the output array with 16-bit bfloat point numbers.

◆ SimdBFloat16ToFloat32()

void SimdBFloat16ToFloat32 ( const uint16_t *  src,
size_t  size,
float *  dst 
)

Converts numbers in the array from 16-bit bfloat to 32-bit float format.

Parameters
[in]src- a pointer to the input array with 16-bit bfloat point numbers.
[in]size- a size of input and output array.
[out]dst- a pointer to the output array with 32-bit float point numbers.