// Copyright 2018 Developers of the Rand project.
//
// Licensed under the Apache License, Version 2.0 <LICENSE-APACHE or
// https://www.apache.org/licenses/LICENSE-2.0> or the MIT license
// <LICENSE-MIT or https://opensource.org/licenses/MIT>, at your
// option. This file may not be copied, modified, or distributed
// except according to those terms.
//! Math helper functions
pub(
crate)
trait WideningMultiply<RHS =
Self> {
type Output;
fn wmul(
self, x: RHS) ->
Self::Output;
}
macro_rules! wmul_impl {
($ty:ty, $wide:ty, $shift:expr) => {
impl WideningMultiply
for $ty {
type Output = ($ty, $ty);
#[inline(always)]
fn wmul(
self, x: $ty) ->
Self::Output {
let tmp = (
self as $wide) * (x
as $wide);
((tmp >> $shift)
as $ty, tmp
as $ty)
}
}
};
// simd bulk implementation
($(($ty:ident, $wide:ident),)+, $shift:expr) => {
$(
impl WideningMultiply
for $ty {
type Output = ($ty, $ty);
#[inline(always)]
fn wmul(
self, x: $ty) ->
Self::Output {
// For supported vectors, this should compile to a couple
// supported multiply & swizzle instructions (no actual
// casting).
// TODO: optimize
let y: $wide =
self.cast();
let x: $wide = x.cast();
let tmp = y * x;
let hi: $ty = (tmp >> $shift).cast();
let lo: $ty = tmp.cast();
(hi, lo)
}
}
)+
};
}
wmul_impl! { u8, u16,
8 }
wmul_impl! { u16, u32,
16 }
wmul_impl! { u32, u64,
32 }
wmul_impl! { u64, u128,
64 }
// This code is a translation of the __mulddi3 function in LLVM's
// compiler-rt. It is an optimised variant of the common method
// `(a + b) * (c + d) = ac + ad + bc + bd`.
//
// For some reason LLVM can optimise the C version very well, but
// keeps shuffling registers in this Rust translation.
macro_rules! wmul_impl_large {
($ty:ty, $half:expr) => {
impl WideningMultiply
for $ty {
type Output = ($ty, $ty);
#[inline(always)]
fn wmul(
self, b: $ty) ->
Self::Output {
const LOWER_MASK: $ty = !
0 >> $half;
let mut low = (
self & LOWER_MASK).wrapping_mul(b & LOWER_MASK);
let mut t = low >> $half;
low &= LOWER_MASK;
t += (
self >> $half).wrapping_mul(b & LOWER_MASK);
low += (t & LOWER_MASK) << $half;
let mut high = t >> $half;
t = low >> $half;
low &= LOWER_MASK;
t += (b >> $half).wrapping_mul(
self & LOWER_MASK);
low += (t & LOWER_MASK) << $half;
high += t >> $half;
high += (
self >> $half).wrapping_mul(b >> $half);
(high, low)
}
}
};
// simd bulk implementation
(($($ty:ty,)+) $scalar:ty, $half:expr) => {
$(
impl WideningMultiply
for $ty {
type Output = ($ty, $ty);
#[inline(always)]
fn wmul(
self, b: $ty) ->
Self::Output {
// needs wrapping multiplication
const LOWER_MASK: $scalar = !
0 >> $half;
let mut low = (
self & LOWER_MASK) * (b & LOWER_MASK);
let mut t = low >> $half;
low &= LOWER_MASK;
t += (
self >> $half) * (b & LOWER_MASK);
low += (t & LOWER_MASK) << $half;
let mut high = t >> $half;
t = low >> $half;
low &= LOWER_MASK;
t += (b >> $half) * (
self & LOWER_MASK);
low += (t & LOWER_MASK) << $half;
high += t >> $half;
high += (
self >> $half) * (b >> $half);
(high, low)
}
}
)+
};
}
wmul_impl_large! { u128,
64 }
macro_rules! wmul_impl_usize {
($ty:ty) => {
impl WideningMultiply
for usize {
type Output = (usize, usize);
#[inline(always)]
fn wmul(
self, x: usize) ->
Self::Output {
let (high, low) = (
self as $ty).wmul(x
as $ty);
(high
as usize, low
as usize)
}
}
};
}
#[cfg(target_pointer_width =
"16")]
wmul_impl_usize! { u16 }
#[cfg(target_pointer_width =
"32")]
wmul_impl_usize! { u32 }
#[cfg(target_pointer_width =
"64")]
wmul_impl_usize! { u64 }
/// Helper trait when dealing with scalar and SIMD floating point types.
pub(
crate)
trait FloatSIMDUtils {
// `PartialOrd` for vectors compares lexicographically. We want to compare all
// the individual SIMD lanes instead, and get the combined result over all
// lanes. This is possible using something like `a.lt(b).all()`, but we
// implement it as a trait so we can write the same code for `f32` and `f64`.
// Only the comparison functions we need are implemented.
fn all_lt(
self, other:
Self) -> bool;
fn all_le(
self, other:
Self) -> bool;
fn all_finite(
self) -> bool;
type Mask;
fn finite_mask(
self) ->
Self::Mask;
fn gt_mask(
self, other:
Self) ->
Self::Mask;
fn ge_mask(
self, other:
Self) ->
Self::Mask;
// Decrease all lanes where the mask is `true` to the next lower value
// representable by the floating-point type. At least one of the lanes
// must be set.
fn decrease_masked(
self, mask:
Self::Mask) ->
Self;
// Convert from int value. Conversion is done while retaining the numerical
// value, not by retaining the binary representation.
type UInt;
fn cast_from_int(i:
Self::UInt) ->
Self;
}
/// Implement functions available in std builds but missing from core primitives
#[cfg(not(feature =
"std"))]
#[allow(unused)]
// False positive: We are following `std` here.
#[allow(clippy::wrong_self_convention)]
pub(
crate)
trait Float: Sized {
fn is_nan(
self) -> bool;
fn is_infinite(
self) -> bool;
fn is_finite(
self) -> bool;
}
/// Implement functions on f32/f64 to give them APIs similar to SIMD types
#[allow(unused)]
pub(
crate)
trait FloatAsSIMD: Sized {
#[inline(always)]
fn lanes() -> usize {
1
}
#[inline(always)]
fn splat(scalar:
Self) ->
Self {
scalar
}
#[inline(always)]
fn extract(
self, index: usize) ->
Self {
debug_assert_eq!(index,
0);
self
}
#[inline(always)]
fn replace(
self, index: usize, new_value:
Self) ->
Self {
debug_assert_eq!(index,
0);
new_value
}
}
#[allow(unused)]
pub(
crate)
trait BoolAsSIMD: Sized {
fn any(
self) -> bool;
fn all(
self) -> bool;
fn none(
self) -> bool;
}
impl BoolAsSIMD
for bool {
#[inline(always)]
fn any(
self) -> bool {
self
}
#[inline(always)]
fn all(
self) -> bool {
self
}
#[inline(always)]
fn none(
self) -> bool {
!
self
}
}
macro_rules! scalar_float_impl {
($ty:ident, $uty:ident) => {
#[cfg(not(feature =
"std"))]
impl Float
for $ty {
#[inline]
fn is_nan(
self) -> bool {
self !=
self
}
#[inline]
fn is_infinite(
self) -> bool {
self == ::core::$ty::INFINITY ||
self == ::core::$ty::NEG_INFINITY
}
#[inline]
fn is_finite(
self) -> bool {
!(
self.is_nan() ||
self.is_infinite())
}
}
impl FloatSIMDUtils
for $ty {
type Mask = bool;
type UInt = $uty;
#[inline(always)]
fn all_lt(
self, other:
Self) -> bool {
self < other
}
#[inline(always)]
fn all_le(
self, other:
Self) -> bool {
self <= other
}
#[inline(always)]
fn all_finite(
self) -> bool {
self.is_finite()
}
#[inline(always)]
fn finite_mask(
self) ->
Self::Mask {
self.is_finite()
}
#[inline(always)]
fn gt_mask(
self, other:
Self) ->
Self::Mask {
self > other
}
#[inline(always)]
fn ge_mask(
self, other:
Self) ->
Self::Mask {
self >= other
}
#[inline(always)]
fn decrease_masked(
self, mask:
Self::Mask) ->
Self {
debug_assert!(mask,
"At least one lane must be set");
<$ty>::from_bits(
self.to_bits() -
1)
}
#[inline]
fn cast_from_int(i:
Self::UInt) ->
Self {
i
as $ty
}
}
impl FloatAsSIMD
for $ty {}
};
}
scalar_float_impl!(f32, u32);
scalar_float_impl!(f64, u64);