This crate implements a half-precision floating point f16
type for Rust implementing the IEEE 754-2008 standard
binary16
a.k.a half
format,
as well as a bf16
type implementing the bfloat16
format.
The f16
and bf16
types provides conversion operations as a normal Rust floating point type, but since they are primarily leveraged for
minimal floating point storage and most major hardware does not implement them, all math operations should be done as an f32
type.
This crate provides no_std
support by default so can easily be used in embedded
code where a smaller float format is most useful.
Requires Rust 1.32 or greater. If you need support for older versions of Rust, use versions 1.3 and earlier of this crate.
See the crate documentation for more details.
-
serde
- ImplementSerialize
andDeserialize
traits forf16
andbf16
. This adds a dependency on theserde
crate. -
use-intrinsics
- Use hardware intrinsics forf16
andbf16
conversions if available on the compiler host target. By default, without this feature, conversions are done only in software, which will be the fallback if the host target does not have hardware support. Available only on Rust nightly channel. -
alloc
- Enable use of thealloc
crate when not using thestd
library.This enables the
vec
module, which contains zero-copy conversions for theVec
type. This allows fast conversion between rawVec<u16>
bits andVec<f16>
orVec<bf16>
arrays, and vice versa. Requires Rust 1.36 or greater. -
std
- Enable features that depend on the Ruststd
library, including everything in thealloc
feature.Enabling the
std
feature enables runtime CPU feature detection when theuse-intrsincis
feature is also enabled. Without this feature detection, intrinsics are only used when compiler host target supports them. -
num-traits
- EnableToPrimitive
,FromPrimitive
,Num
,Float
, andFloatCore
trait implementations from thenum-traits
crate. -
bytemuck
- EnableZeroable
andPod
trait implementations from thebytemuck
crate.
This library is distributed under the terms of either of:
- MIT license (LICENSE-MIT or https://opensource.org/licenses/MIT)
- Apache License, Version 2.0 (LICENSE-APACHE or https://www.apache.org/licenses/LICENSE-2.0)
at your option.
Unless you explicitly state otherwise, any contribution intentionally submitted for inclusion in the work by you, as defined in the Apache-2.0 license, shall be dual licensed as above, without any additional terms or conditions.