Ref.https://github.com/starkat99/half-rs/blob/cabfc74e2a48b44b4556780f9d1550dd50a708be/src/bfloat/convert.rs#L5C1-L24C1.

Frombits returns the float16 number corresponding to the IEEE 754 binary16 representation u16, with the sign bit of u16 and the result in the same bit position.

Fromfloat32 returns a Float16 value converted from f32.

FromNaN32ps converts nan to IEEE binary16 NaN while preserving both signaling and payload.

Inf returns a Float16 with an infinity value with the specified sign.

NaN returns a Float16 of IEEE 754 binary16 not-a-number (NaN).

PrecisionFromfloat32 returns Precision without performing the conversion.

ErrInvalidNaNValue indicates a NaN was not received.

PrecisionExact is for non-subnormals that don't drop bits during conversion.

PrecisionInexact is for dropped significand bits and cannot round-trip.

PrecisionOverflow is for Overflows.

PrecisionUnderflow is for Underflows.

PrecisionUnknown is for subnormals that don't drop bits during conversion but not all of these can round-trip so precision is unknown without more effort.

The bfloat16 - Google 'brain' floating point format is a truncated 16-bit version of the IEEE 754 standard binary32.

Float16 represents IEEE 754 half-precision floating-point numbers (binary16).

Precision indicates whether the conversion to Float16 is exact, subnormal without dropped bits, inexact, underflow, or overflow.