Struct f16 Copy item path

impl f16

pub const DIGITS: u32 = 3u32

Approximate number of f16 significant digits in base 10

pub const EPSILON: f16

f16 machine epsilon value

pub const fn from_f32_const(value: f32) -> f16

Constructs a 16-bit floating point value from a 32-bit floating point value.

This function is identical to from_f32 except it never uses hardware intrinsics, which allows it to be const. from_f32 should be preferred in any non-const context.

This operation is lossy. If the 32-bit value is to large to fit in 16-bits, ±∞ will result. NaN values are preserved. 32-bit subnormal values are too tiny to be represented in 16-bits and result in ±0. Exponents that underflow the minimum 16-bit exponent will result in 16-bit subnormals or ±0. All other values are truncated and rounded to the nearest representable 16-bit value.

pub fn from_f64(value: f64) -> f16

Constructs a 16-bit floating point value from a 64-bit floating point value.

This operation is lossy. If the 64-bit value is to large to fit in 16-bits, ±∞ will result. NaN values are preserved. 64-bit subnormal values are too tiny to be represented in 16-bits and result in ±0. Exponents that underflow the minimum 16-bit exponent will result in 16-bit subnormals or ±0. All other values are truncated and rounded to the nearest representable 16-bit value.

pub const fn from_f64_const(value: f64) -> f16

Constructs a 16-bit floating point value from a 64-bit floating point value.

This function is identical to from_f64 except it never uses hardware intrinsics, which allows it to be const. from_f64 should be preferred in any non-const context.

This operation is lossy. If the 64-bit value is to large to fit in 16-bits, ±∞ will result. NaN values are preserved. 64-bit subnormal values are too tiny to be represented in 16-bits and result in ±0. Exponents that underflow the minimum 16-bit exponent will result in 16-bit subnormals or ±0. All other values are truncated and rounded to the nearest representable 16-bit value.

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]
});

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));

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));

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));

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.

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.

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.

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());

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);

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());

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());

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());

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());

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);

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);

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());

pub fn total_cmp(&self, other: &f16) -> 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()));

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

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
}

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

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
}

fn __expand_clamp( scope: &mut Scope, input: Self::ExpandType, min_value: Self::ExpandType, max_value: Self::ExpandType, ) -> Self::ExpandType

impl Clone for f16

fn clone(&self) -> f16

Returns a copy of the value. Read more

1.0.0 · Source§

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source. Read more

fn as_elem(_context: &Scope) -> Elem

Return the element type to use on GPU.

fn as_elem_native_unchecked() -> Elem

Native or static element type.

fn size() -> Option<usize>

Only native element types have a size.

fn floor(x: Self) -> Self

fn from_be_bytes(bytes: &<f16 as FromBytes>::Bytes) -> f16

Create a number from its representation as a byte array in big endian. Read more

fn from_le_bytes(bytes: &<f16 as FromBytes>::Bytes) -> f16

Create a number from its representation as a byte array in little endian. Read more

fn from_ne_bytes(bytes: &<f16 as FromBytes>::Bytes) -> f16

Create a number from its memory representation as a byte array in native endianness. Read more

Convert all values from the slice into this type. This function exists to allow the compiler to perform a vectorization optimization. Note that this default implementation will be vectorized by the compiler automatically, provided that the CPU supports the necessary conversion instructions. For example, x86_64 lacks the instructions to convert u32 to floats, so this will inevitably be slow on x86_64.

Converts an u128 to return an optional value of this type. If the value cannot be represented by this type, then None is returned. Read more

impl FromStr for f16

type Err = ParseFloatError

The associated error which can be returned from parsing.

fn from_str(src: &str) -> Result<f16, ParseFloatError>

Parses a string s to return a value of this type. Read more

impl IntoNativeSample for f16

fn to_f16(&self) -> f16

Convert this sample to an f16, trying to represent the same numerical value.

fn to_f32(&self) -> f32

Convert this sample to an f32, trying to represent the same numerical value.

fn to_u32(&self) -> u32

Convert this sample to an u16, trying to represent the same numerical value.

impl LaunchArgExpand for f16

type CompilationArg = ()

Compilation argument.

fn expand( _: &<f16 as LaunchArgExpand>::CompilationArg, builder: &mut KernelBuilder, ) -> ExpandElementTyped<f16>

Register an input variable during compilation that fill the [KernelBuilder].

fn expand_output( arg: &Self::CompilationArg, builder: &mut KernelBuilder, ) -> Self::ExpandType

Register an output variable during compilation that fill the [KernelBuilder].

Formats the value using the given formatter. Read more

impl LowerHex for f16

fn fmt(&self, f: &mut Formatter<'_>) -> Result<(), Error>

Formats the value using the given formatter. Read more

Element type of each input tensors of the kernel.

type ES = f16

Element type for the shared memories used to read inputs.

type EA = f32

Element type for the shared memories or fragments used to accumulate smaller matmul results before writing to the output tensor.

type EO = f16

Element type of the output tensor of the kernel.

fn format(&self, passed_settings: DisplaySettings) -> String

fn neg(self) -> <&f16 as Neg>::Output

Performs the unary - operation. Read more

impl Neg for f16

type Output = f16

The resulting type after applying the - operator.

fn neg(self) -> <f16 as Neg>::Output

Performs the unary - operation. Read more

Convert from a string and radix (typically 2..=36). Read more

impl NumCast for f16