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
|
#[lang = "sized"]
pub trait Sized {}
mod intrinsics {
extern "rust-intrinsic" {
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 = 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 replace<T>(dest: &mut T, mut src: T) -> T {
swap(dest, &mut src);
src
}
pub unsafe fn uninitialized<T>() -> T {
intrinsics::uninit()
}
}
trait Step {
fn replace_zero(&mut self) -> Self;
}
impl Step for i32 {
fn replace_zero(&mut self) -> Self {
mem::replace(self, 0)
}
}
fn main() -> i32 {
let a = 123;
a.replace_zero();
a
}
|
