Function fmin

include/half.hpp:2889–2893

Minimum of half expressions. See also:** Documentation for [std::fmin](https://en.cppreference.com/w/cpp/numeric/math/fmin). \param x first operand \param y second operand \return minimum of operands, ignoring quiet NaNs \exception FE_INVALID if \a x or \a y is signaling NaN

	/// \return minimum of operands, ignoring quiet NaNs
	/// \exception FE_INVALID if \a x or \a y is signaling NaN
	inline HALF_CONSTEXPR_NOERR half fmin(half x, half y)
	{
		return half(detail::binary, (!isnan(y) && (isnan(x) || (x.data_^(0x8000|(0x8000-(x.data_>>15)))) >
			(y.data_^(0x8000|(0x8000-(y.data_>>15)))))) ? detail::select(y.data_, x.data_) : detail::select(x.data_, y.data_));
	}

	/// Positive difference.
	/// This function is exact to rounding for all rounding modes.