[−][src]Crate half
A crate that provides support for half-precision 16-bit floating point types.
This crate provides the f16
type, which is an implementation of the IEEE 754-2008 standard
binary16
a.k.a half
floating point type. 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. This is especially useful for image storage formats.
This crate also provides a bf16
type, an alternative 16-bit floating point format. The
bfloat16
format is a truncated IEEE 754 standard binary32
float that preserves the
exponent to allow the same range as f32
but with only 8 bits of precision (instead of 11
bits for f16
). See the bf16
type for details.
Because f16
and bf16
are primarily for efficient storage, floating point operations such as
addition, multiplication, etc. are not implemented. Operations should be performed with f32
or higher-precision types and converted to/from f16
or bf16
as necessary.
This crate also provides a slice
module for zero-copy in-place conversions of u16
slices
to both f16
and bf16
, as well as efficient vectorized conversions of larger buffers of
floating point values to and from these half formats.
A prelude
module is provided for easy importing of available utility traits.
Some hardware architectures provide support for 16-bit floating point conversions. Enable the
use-intrinsics
feature to use LLVM intrinsics for hardware conversions. This crate does no
checks on whether the hardware supports the feature. This feature currently only works on
nightly Rust due to a compiler feature gate. When this feature is enabled and the hardware
supports it, the slice
trait conversions will use vectorized SIMD intructions for
increased efficiency.
Support for serde
crate Serialize
and Deserialize
traits is provided when the serde
feature is enabled. This adds a dependency on serde
crate so is an optional cargo feature.
The crate uses #[no_std]
by default, so can be used in embedded environments without using the
Rust std
library. A std
feature is available, which enables additional utilities using the
std
library, such as the vec
module that provides zero-copy Vec
conversions. The alloc
feature may be used to enable the vec
module without adding a dependency to the std
library.
Modules
consts | Deprecated Useful |
prelude | A collection of the most used items and traits in this crate for easy importing. |
slice | Contains utility functions and traits to convert between slices of |
Structs
bf16 | A 16-bit floating point type implementing the |
f16 | A 16-bit floating point type implementing the IEEE 754-2008 standard |