Cast (float to bfloat16_t)

Applicability

Product	Supported
Atlas 350 Accelerator Card	√
Atlas A3 training product/Atlas A3 inference product	√
Atlas A2 training product/Atlas A2 inference product	√
Atlas 200I/500 A2 inference product	x
Atlas inference product AI Core	x
Atlas inference product Vector Core	x
Atlas training product	x

Function Usage

Converts scalar data of the float type to scalar data of the bfloat16_t type.

Prototype

__aicore__ inline bfloat16_t Cast(const float& fVal)

Parameters

**Table 1** API parameters
Parameter	Input/Output	Meaning
fVal	Input	Scalar data of the float type.

Returns

Converted scalar data of the bfloat16_t type.

Constraints

None

Example

float m = 3.0f;
bfloat16_t n = AscendC::Cast(m); // n = 3.0. The exponent and mantissa expressions of bfloat16_t and float are different. Truncation can be used for conversion.

Parent topic: Scalar Computation