native::bf16 Struct Reference

Public Types
using	underlying_type = __bf16
	Native half storage when supported by the target; otherwise sixteen raw bits.

Public Member Functions
constexpr	bf16 () noexcept=default
	Default-initialize storage without setting its bits; value-initialization zeroes it.
constexpr	bf16 (float f) noexcept
	Round a binary32 value to this format, ties to even.
constexpr	bf16 (__bf16 f) noexcept
	Copy native storage without a numerical conversion.
constexpr	bf16 (bf16 const &) noexcept=default
	Copy the native sixteen-bit representation.
constexpr	bf16 (bf16 &&) noexcept=default
	Copy the native representation; the source retains its bits.
constexpr	operator __bf16 (this bf16 self) noexcept
	Return native storage without rounding or normalizing NaN payloads.
constexpr	operator float (this bf16 self) noexcept
	Decode to binary32; finite values are exact and signaling NaNs are quieted.
constexpr bf16 &	operator= (bf16 const &) noexcept=default
	Copy the native representation, replacing all previous bits.
constexpr bf16 &	operator= (bf16 &&) noexcept=default
	Copy the native representation, leaving the source unchanged.
constexpr uint16_t	to_bits (this bf16 self) noexcept
	Return the exact sixteen representation bits.

Static Public Member Functions
static constexpr bf16	from_bits (uint16_t data) noexcept
	Adopt the exact sixteen representation bits without normalization.

Public Attributes
underlying_type	content
	Target-dependent storage. Use to_bits()/from_bits() for portable representation access.

Friends
constexpr bool	operator== (bf16 x, bf16 y) noexcept
	Compare decoded values for equality; signed zeros compare equal and NaNs do not.
constexpr std::partial_ordering	operator<=> (bf16 x, bf16 y) noexcept
	Compare decoded values; NaNs are unordered and signed zeros equivalent.
constexpr bool	operator!= (bf16 x, bf16 y) noexcept
	Compare decoded values for inequality; a NaN operand makes the result true.
constexpr bool	operator< (bf16 x, bf16 y) noexcept
	Return whether the decoded left value is less; false for NaN operands.
constexpr bool	operator> (bf16 x, bf16 y) noexcept
	Return whether the decoded left value is greater; false for NaN operands.
constexpr bool	operator<= (bf16 x, bf16 y) noexcept
	Return whether the decoded left value is at most the right; false for NaN operands.
constexpr bool	operator>= (bf16 x, bf16 y) noexcept
	Return whether the decoded left value is at least the right; false for NaN operands.
constexpr void	swap (bf16 &x, bf16 &y) noexcept
	Exchange native representations, including signed zeros and NaN payloads.

Detailed Description

Two-byte bfloat16 storage with environment-independent binary32 ties-to-even conversion. Native-bfloat interoperability is available only where the target supports it. Native import and bit factories preserve representation. No arithmetic or FTZ policy is attached to the storage type.

Definition at line 300 of file native.numerics.ccm.

---

The documentation for this struct was generated from the following file:

• src/native.numerics.ccm