1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
|
// { dg-options "-w" }
#![feature(intrinsics)]
pub use option::Option::{self, None, Some};
pub use result::Result::{self, Err, Ok};
mod option {
pub enum Option<T> {
None,
Some(T),
}
}
mod result {
pub enum Result<T, E> {
Ok(T),
Err(E),
}
}
#[lang = "sized"]
pub trait Sized {}
#[lang = "clone"]
pub trait Clone: Sized {
fn clone(&self) -> Self;
fn clone_from(&mut self, source: &Self) {
*self = source.clone()
}
}
mod impls {
use super::Clone;
macro_rules! impl_clone {
($($t:ty)*) => {
$(
impl Clone for $t {
fn clone(&self) -> Self {
*self
}
}
)*
}
}
impl_clone! {
usize u8 u16 u32 u64 // u128
isize i8 i16 i32 i64 // i128
f32 f64
bool char
}
}
#[lang = "copy"]
pub trait Copy: Clone {
// Empty.
}
mod copy_impls {
use super::Copy;
macro_rules! impl_copy {
($($t:ty)*) => {
$(
impl Copy for $t {}
)*
}
}
impl_copy! {
usize u8 u16 u32 u64 // u128
isize i8 i16 i32 i64 // i128
f32 f64
bool char
}
}
mod intrinsics {
extern "rust-intrinsic" {
pub fn add_with_overflow<T>(x: T, y: T) -> (T, bool);
pub fn wrapping_add<T>(a: T, b: T) -> T;
pub fn wrapping_sub<T>(a: T, b: T) -> T;
pub fn rotate_left<T>(a: T, b: T) -> T;
pub fn rotate_right<T>(a: T, b: T) -> T;
pub fn offset<T>(ptr: *const T, count: isize) -> *const T;
pub fn copy_nonoverlapping<T>(src: *const T, dst: *mut T, count: usize);
pub fn move_val_init<T>(dst: *mut T, src: T);
pub fn uninit<T>() -> T;
}
}
mod ptr {
#[lang = "const_ptr"]
impl<T> *const T {
pub unsafe fn offset(self, count: isize) -> *const T {
intrinsics::offset(self, count)
}
}
#[lang = "mut_ptr"]
impl<T> *mut T {
pub unsafe fn offset(self, count: isize) -> *mut T {
intrinsics::offset(self, count) as *mut T
}
}
pub unsafe fn swap_nonoverlapping<T>(x: *mut T, y: *mut T, count: usize) {
let x = x as *mut u8;
let y = y as *mut u8;
let len = mem::size_of::<T>() * count;
swap_nonoverlapping_bytes(x, y, len)
}
pub unsafe fn swap_nonoverlapping_one<T>(x: *mut T, y: *mut T) {
// For types smaller than the block optimization below,
// just swap directly to avoid pessimizing codegen.
if mem::size_of::<T>() < 32 {
let z = read(x);
intrinsics::copy_nonoverlapping(y, x, 1);
write(y, z);
} else {
swap_nonoverlapping(x, y, 1);
}
}
pub unsafe fn write<T>(dst: *mut T, src: T) {
intrinsics::move_val_init(&mut *dst, src)
}
pub unsafe fn read<T>(src: *const T) -> T {
let mut tmp: T = mem::uninitialized();
intrinsics::copy_nonoverlapping(src, &mut tmp, 1);
tmp
}
unsafe fn swap_nonoverlapping_bytes(x: *mut u8, y: *mut u8, len: usize) {
struct Block(u64, u64, u64, u64);
struct UnalignedBlock(u64, u64, u64, u64);
let block_size = mem::size_of::<Block>();
// Loop through x & y, copying them `Block` at a time
// The optimizer should unroll the loop fully for most types
// N.B. We can't use a for loop as the `range` impl calls `mem::swap` recursively
let mut i: usize = 0;
while i + block_size <= len {
// Create some uninitialized memory as scratch space
// Declaring `t` here avoids aligning the stack when this loop is unused
let mut t: Block = mem::uninitialized();
let t = &mut t as *mut _ as *mut u8;
let x = x.offset(i as isize);
let y = y.offset(i as isize);
// Swap a block of bytes of x & y, using t as a temporary buffer
// This should be optimized into efficient SIMD operations where available
intrinsics::copy_nonoverlapping(x, t, block_size);
intrinsics::copy_nonoverlapping(y, x, block_size);
intrinsics::copy_nonoverlapping(t, y, block_size);
i += block_size;
}
if i < len {
// Swap any remaining bytes
let mut t: UnalignedBlock = mem::uninitialized();
let rem = len - i;
let t = &mut t as *mut _ as *mut u8;
let x = x.offset(i as isize);
let y = y.offset(i as isize);
intrinsics::copy_nonoverlapping(x, t, rem);
intrinsics::copy_nonoverlapping(y, x, rem);
intrinsics::copy_nonoverlapping(t, y, rem);
}
}
}
mod mem {
extern "rust-intrinsic" {
pub fn transmute<T, U>(_: T) -> U;
pub fn size_of<T>() -> usize;
}
pub fn swap<T>(x: &mut T, y: &mut T) {
unsafe {
ptr::swap_nonoverlapping_one(x, y);
}
}
pub fn test(dest: &mut i32, mut src: i32) -> i32 {
swap(dest, &mut src);
src
}
pub unsafe fn uninitialized<T>() -> T {
intrinsics::uninit()
}
}
|
