Struct half::f16

source ·

pub struct f16(/* private fields */);

Expand description

A 16-bit floating point type implementing the IEEE 754-2008 standard binary16 a.k.a “half” format.

This 16-bit floating point type is intended for efficient storage where the full range and precision of a larger floating point value is not required.

Implementations§

Returns the memory representation of the underlying bit representation as a byte array in native byte order.

As the target platform’s native endianness is used, portable code should use to_be_bytes or to_le_bytes, as appropriate, instead.

§Examples

let bytes = f16::from_f32(12.5).to_ne_bytes();
assert_eq!(bytes, if cfg!(target_endian = "big") {
    [0x4A, 0x40]
} else {
    [0x40, 0x4A]
});

source

pub const fn from_le_bytes(bytes: [u8; 2]) -> f16

Creates a floating point value from its representation as a byte array in little endian.

§Examples

let value = f16::from_le_bytes([0x40, 0x4A]);
assert_eq!(value, f16::from_f32(12.5));

source

pub const fn from_be_bytes(bytes: [u8; 2]) -> f16

Creates a floating point value from its representation as a byte array in big endian.

§Examples

let value = f16::from_be_bytes([0x4A, 0x40]);
assert_eq!(value, f16::from_f32(12.5));

source

pub const fn from_ne_bytes(bytes: [u8; 2]) -> f16

Creates a floating point value from its representation as a byte array in native endian.

As the target platform’s native endianness is used, portable code likely wants to use from_be_bytes or from_le_bytes, as appropriate instead.

§Examples

let value = f16::from_ne_bytes(if cfg!(target_endian = "big") {
    [0x4A, 0x40]
} else {
    [0x40, 0x4A]
});
assert_eq!(value, f16::from_f32(12.5));

source

pub fn to_f32(self) -> f32

Converts a f16 value into a f32 value.

This conversion is lossless as all 16-bit floating point values can be represented exactly in 32-bit floating point.

source

pub const fn to_f32_const(self) -> f32

Converts a f16 value into a f32 value.

This function is identical to to_f32 except it never uses hardware intrinsics, which allows it to be const. to_f32 should be preferred in any non-const context.

This conversion is lossless as all 16-bit floating point values can be represented exactly in 32-bit floating point.

source

pub fn to_f64(self) -> f64

Converts a f16 value into a f64 value.

This conversion is lossless as all 16-bit floating point values can be represented exactly in 64-bit floating point.

source

pub const fn to_f64_const(self) -> f64

Converts a f16 value into a f64 value.

This function is identical to to_f64 except it never uses hardware intrinsics, which allows it to be const. to_f64 should be preferred in any non-const context.


let min = f16::MIN_POSITIVE;
let max = f16::MAX;
let lower_than_min = f16::from_f32(1.0e-10_f32);
let zero = f16::from_f32(0.0_f32);

assert!(min.is_normal());
assert!(max.is_normal());

assert!(!zero.is_normal());
assert!(!f16::NAN.is_normal());
assert!(!f16::INFINITY.is_normal());
// Values between `0` and `min` are Subnormal.
assert!(!lower_than_min.is_normal());

source

pub const fn classify(self) -> FpCategory

Returns the floating point category of the number.

If only one property is going to be tested, it is generally faster to use the specific predicate instead.

§Examples

use std::num::FpCategory;

let num = f16::from_f32(12.4_f32);
let inf = f16::INFINITY;

assert_eq!(num.classify(), FpCategory::Normal);
assert_eq!(inf.classify(), FpCategory::Infinite);

source

pub const fn signum(self) -> f16

Returns a number that represents the sign of self.

1.0 if the number is positive, +0.0 or INFINITY
-1.0 if the number is negative, -0.0 or NEG_INFINITY
NAN if the number is NaN

§Examples


let f = f16::from_f32(3.5_f32);

assert_eq!(f.signum(), f16::from_f32(1.0));
assert_eq!(f16::NEG_INFINITY.signum(), f16::from_f32(-1.0));

assert!(f16::NAN.signum().is_nan());

source

pub const fn is_sign_positive(self) -> bool

Returns true if and only if self has a positive sign, including +0.0, NaNs with a positive sign bit and +∞.

§Examples


let nan = f16::NAN;
let f = f16::from_f32(7.0_f32);
let g = f16::from_f32(-7.0_f32);

assert!(f.is_sign_positive());
assert!(!g.is_sign_positive());
// `NaN` can be either positive or negative
assert!(nan.is_sign_positive() != nan.is_sign_negative());

source

pub const fn is_sign_negative(self) -> bool

Returns true if and only if self has a negative sign, including -0.0, NaNs with a negative sign bit and −∞.

§Examples


let nan = f16::NAN;
let f = f16::from_f32(7.0f32);
let g = f16::from_f32(-7.0f32);

assert!(!f.is_sign_negative());
assert!(g.is_sign_negative());
// `NaN` can be either positive or negative
assert!(nan.is_sign_positive() != nan.is_sign_negative());

source

pub const fn copysign(self, sign: f16) -> f16

Returns a number composed of the magnitude of self and the sign of sign.

Equal to self if the sign of self and sign are the same, otherwise equal to -self. If self is NaN, then NaN with the sign of sign is returned.

§Examples

let f = f16::from_f32(3.5);

assert_eq!(f.copysign(f16::from_f32(0.42)), f16::from_f32(3.5));
assert_eq!(f.copysign(f16::from_f32(-0.42)), f16::from_f32(-3.5));
assert_eq!((-f).copysign(f16::from_f32(0.42)), f16::from_f32(3.5));
assert_eq!((-f).copysign(f16::from_f32(-0.42)), f16::from_f32(-3.5));

assert!(f16::NAN.copysign(f16::from_f32(1.0)).is_nan());

source

pub fn max(self, other: f16) -> f16

Returns the maximum of the two numbers.

If one of the arguments is NaN, then the other argument is returned.

§Examples

let x = f16::from_f32(1.0);
let y = f16::from_f32(2.0);

assert_eq!(x.max(y), y);

source

pub fn min(self, other: f16) -> f16

Returns the minimum of the two numbers.

If one of the arguments is NaN, then the other argument is returned.

§Examples

let x = f16::from_f32(1.0);
let y = f16::from_f32(2.0);

assert_eq!(x.min(y), x);

source

pub fn clamp(self, min: f16, max: f16) -> f16

Restrict a value to a certain interval unless it is NaN.

Returns max if self is greater than max, and min if self is less than min. Otherwise this returns self.

Note that this function returns NaN if the initial value was NaN as well.

§Panics

Panics if min > max, min is NaN, or max is NaN.

§Examples

assert!(f16::from_f32(-3.0).clamp(f16::from_f32(-2.0), f16::from_f32(1.0)) == f16::from_f32(-2.0));
assert!(f16::from_f32(0.0).clamp(f16::from_f32(-2.0), f16::from_f32(1.0)) == f16::from_f32(0.0));
assert!(f16::from_f32(2.0).clamp(f16::from_f32(-2.0), f16::from_f32(1.0)) == f16::from_f32(1.0));
assert!(f16::NAN.clamp(f16::from_f32(-2.0), f16::from_f32(1.0)).is_nan());

source

pub fn total_cmp(&self, other: &Self) -> Ordering

Returns the ordering between self and other.

Unlike the standard partial comparison between floating point numbers, this comparison always produces an ordering in accordance to the totalOrder predicate as defined in the IEEE 754 (2008 revision) floating point standard. The values are ordered in the following sequence:

negative quiet NaN
negative signaling NaN
negative infinity
negative numbers
negative subnormal numbers
negative zero
positive zero
positive subnormal numbers
positive numbers
positive infinity
positive signaling NaN
positive quiet NaN.

The ordering established by this function does not always agree with the PartialOrd and PartialEq implementations of f16. For example, they consider negative and positive zero equal, while total_cmp doesn’t.

The interpretation of the signaling NaN bit follows the definition in the IEEE 754 standard, which may not match the interpretation by some of the older, non-conformant (e.g. MIPS) hardware implementations.

§Examples

let mut v: Vec<f16> = vec![];
v.push(f16::ONE);
v.push(f16::INFINITY);
v.push(f16::NEG_INFINITY);
v.push(f16::NAN);
v.push(f16::MAX_SUBNORMAL);
v.push(-f16::MAX_SUBNORMAL);
v.push(f16::ZERO);
v.push(f16::NEG_ZERO);
v.push(f16::NEG_ONE);
v.push(f16::MIN_POSITIVE);

v.sort_by(|a, b| a.total_cmp(&b));

assert!(v
    .into_iter()
    .zip(
        [
            f16::NEG_INFINITY,
            f16::NEG_ONE,
            -f16::MAX_SUBNORMAL,
            f16::NEG_ZERO,
            f16::ZERO,
            f16::MAX_SUBNORMAL,
            f16::MIN_POSITIVE,
            f16::ONE,
            f16::INFINITY,
            f16::NAN
        ]
        .iter()
    )
    .all(|(a, b)| a.to_bits() == b.to_bits()));

source

pub fn serialize_as_f32<S: Serializer>( &self, serializer: S ) -> Result<S::Ok, S::Error>

Available on crate feature serde only.

Alternate serialize adapter for serializing as a float.

By default, f16 serializes as a newtype of u16. This is an alternate serialize implementation that serializes as an f32 value. It is designed for use with serialize_with serde attributes. Deserialization from f32 values is already supported by the default deserialize implementation.

§Examples

A demonstration on how to use this adapater:

use serde::{Serialize, Deserialize};
use half::f16;

#[derive(Serialize, Deserialize)]
struct MyStruct {
    #[serde(serialize_with = "f16::serialize_as_f32")]
    value: f16 // Will be serialized as f32 instead of u16
}

source

pub fn serialize_as_string<S: Serializer>( &self, serializer: S ) -> Result<S::Ok, S::Error>

Available on crate features serde and alloc only.

Alternate serialize adapter for serializing as a string.

By default, f16 serializes as a newtype of u16. This is an alternate serialize implementation that serializes as a string value. It is designed for use with serialize_with serde attributes. Deserialization from string values is already supported by the default deserialize implementation.

§Examples

A demonstration on how to use this adapater:

use serde::{Serialize, Deserialize};
use half::f16;

#[derive(Serialize, Deserialize)]
struct MyStruct {
    #[serde(serialize_with = "f16::serialize_as_string")]
    value: f16 // Will be serialized as a string instead of u16
}

source