为什么将函数移动到结构上的方法时 #[inline] 属性停止工作？
Why does the #[inline] attribute stop working when a function is moved to a method on a struct?
我有函数 get_screen，它在 main.rs 的单独模块中指定。它需要两个 2D 向量（一个是 1920x1080，称为 screen，另一个更大，称为 world）并将 world 向量的一部分映射到 screen 向量。这是我第一次做的时候的函数签名：
pub fn get_screen(
screen: &mut Vec<Vec<[u8; 4]>>,
world: &Vec<Vec<Chunk>>,
camera_coords: (isize, isize),
screen_width: usize,
screen_height: usize,
chunk_width: usize,
chunk_height: usize,
)
我在执行时间上遇到了严重的问题，但我通过使用 #[inline].
将其从 14 毫秒优化到 3 毫秒
然后我将 world 向量移动到它自己的结构中（连同一些其他相关变量，如块 width/height）并将 get_screen 函数变成新 world 结构。这是更改后的函数签名的样子：
pub fn get_screen(
&self,
screen: &mut Vec<Vec<[u8; 4]>>,
camera_coords: (isize, isize),
screen_width: usize,
screen_height: usize,
)
然后执行时间增加回 14 毫秒。我试过在 Cargo.toml 中启用 lto=true 并切换到 #[inline(always)] 来强制执行它，但编译器似乎拒绝像以前那样优化此功能。
我试图从结构中删除 get_screen 方法并 运行 它像以前一样作为自己的函数，这似乎修复了它，但是 只有 如果我不从结构中传递任何东西。如果我尝试将 usize 从 world 结构传递到单独的 get_screen 函数，则执行时间会从 3 毫秒增加回 14 毫秒。
举个例子来说明我的意思，如果我不直接从 world 结构传递任何内容，而是将 world 中的 2D 结构的克隆版本和硬编码的 chunk_width/chunk_height:
gen::get_screen(
&mut screen.buf,
&cloned_world_data,
camera_coords,
SCREEN_WIDTH,
SCREEN_HEIGHT,
CHUNK_WIDTH,
CHUNK_HEIGHT,
);
它在 3.3 毫秒内 运行 秒。当我直接从 world 结构传递 usize 字段 chunk_width/chunk_height 时：
gen::get_screen(
&mut screen.buf,
&cloned_world_data,
camera_coords,
SCREEN_WIDTH,
SCREEN_HEIGHT,
world.chunk_width,
world.chunk_height,
);
运行
需要 14.55 毫秒
这里有什么？如何在使用我的 World 结构时让我的 get_screen 函数内联编译？最好我希望能够将它作为一种方法重新添加到我的 World 结构中，而不是将其分开。
这是一个最小的例子：
use std::time::Instant;
const SCREEN_HEIGHT: usize = 1080; //528;
const SCREEN_WIDTH: usize = 1920; //960;
const CHUNK_WIDTH: usize = 256;
const CHUNK_HEIGHT: usize = 256;
const GEN_RANGE: isize = 25; //how far out to gen chunks
fn main() {
let batch_size = 1_000;
struct_test(batch_size);
separate_test(batch_size);
}
fn struct_test(batch_size: u32) {
let world = World::new(CHUNK_WIDTH, CHUNK_HEIGHT, GEN_RANGE); //generate world
let mut screen = vec![vec!([0; 4]; SCREEN_WIDTH); SCREEN_HEIGHT];
let camera_coords: (isize, isize) = (0, 0); //set camera location
let start = Instant::now();
for _ in 0..batch_size {
get_screen(
&mut screen,
&world.data,
camera_coords,
SCREEN_WIDTH,
SCREEN_HEIGHT,
world.chunk_width,
world.chunk_height,
); //gets visible pixels from world as 2d vec
}
println!(
"struct: {:?} {:?}",
start.elapsed(),
start.elapsed() / batch_size
);
}
fn separate_test(batch_size: u32) {
let world = World::new(CHUNK_WIDTH, CHUNK_HEIGHT, GEN_RANGE); //generate world
let cloned_world_data = world.data.clone();
let mut screen = vec![vec!([0; 4]; SCREEN_WIDTH); SCREEN_HEIGHT];
let camera_coords: (isize, isize) = (0, 0); //set camera location
let start = Instant::now();
for _ in 0..batch_size {
get_screen(
&mut screen,
&cloned_world_data,
camera_coords,
SCREEN_WIDTH,
SCREEN_HEIGHT,
CHUNK_WIDTH,
CHUNK_HEIGHT,
); //gets visible pixels from world as 2d vec
}
println!(
"separate: {:?} {:?}",
start.elapsed(),
start.elapsed() / batch_size
);
}
///gets all visible pixels on screen relative camera position in world
#[inline(always)] //INLINE STOPPED WORKING??
pub fn get_screen(
screen: &mut Vec<Vec<[u8; 4]>>,
world: &Vec<Vec<Chunk>>,
camera_coords: (isize, isize),
screen_width: usize,
screen_height: usize,
chunk_width: usize,
chunk_height: usize,
) {
let camera = get_local_coords(&world, camera_coords, chunk_width, chunk_height); //gets loaded coords of camera in loaded chunks
(camera.1 - screen_height as isize / 2..camera.1 + screen_height as isize / 2)
.enumerate()
.for_each(|(py, y)| {
//for screen pixel index and particle in range of camera loaded y
let (cy, ly) = get_local_pair(y, chunk_height); //calculate chunk y and inner y from loaded y
if let Some(c_row) = world.get(cy) {
//if chunk row at loaded chunk y exists
(camera.0 - screen_width as isize / 2..camera.0 + screen_width as isize / 2)
.enumerate()
.for_each(|(px, x)| {
//for screen pixel index and particle in range of camera loaded x
let (cx, lx) = get_local_pair(x, chunk_width); //get loaded chunk x and inner x from loaded x
if let Some(c) = c_row.get(cx) {
screen[py][px] = c.data[ly][lx];
}
//if chunk in row then copy color of target particle in chunk
else {
screen[py][px] = [0; 4]
} //if target chunk doesn't exist color black
})
} else {
screen[py].iter_mut().for_each(|px| *px = [0; 4])
} //if target chunk row doesn't exist color row black
});
}
///calculates local coordinates in world vec from your global position
///returns negative if above/left of rendered area
pub fn get_local_coords(
world: &Vec<Vec<Chunk>>,
coords: (isize, isize),
chunk_width: usize,
chunk_height: usize,
) -> (isize, isize) {
let (wx, wy) = world[0][0].chunk_coords; //gets coords of first chunk in rendered vec
let lx = coords.0 - (wx * chunk_width as isize); //calculates local x coord based off world coords of first chunk
let ly = (wy * chunk_height as isize) - coords.1; //calculates local y coord based off world coords of first chunk
(lx, ly)
}
pub fn get_local_pair(coord: isize, chunk: usize) -> (usize, usize) {
(coord as usize / chunk, coord as usize % chunk)
}
///contains chunk data
#[derive(Clone)]
pub struct Chunk {
//world chunk object
pub chunk_coords: (isize, isize), //chunk coordinates
pub data: Vec<Vec<[u8; 4]>>, //chunk Particle data
}
impl Chunk {
///generates chunk
fn new(chunk_coords: (isize, isize), chunk_width: usize, chunk_height: usize) -> Self {
let data = vec![vec!([0; 4]; chunk_width); chunk_height];
Self { chunk_coords, data }
}
}
pub struct World {
pub data: Vec<Vec<Chunk>>,
pub chunk_width: usize,
pub chunk_height: usize,
}
impl World {
pub fn new(chunk_width: usize, chunk_height: usize, gen_range: isize) -> Self {
let mut data = Vec::new(); //creates empty vec to hold world
for (yi, world_chunk_y) in (gen_range * -1..gen_range + 1).rev().enumerate() {
//for y index, y in gen range counting down
data.push(Vec::new()); //push new row
for world_chunk_x in gen_range * -1..gen_range + 1 {
//for chunk in gen range of row
data[yi].push(Chunk::new(
(world_chunk_x, world_chunk_y),
chunk_width,
chunk_height,
)); //gen new chunk and put it there
}
}
Self {
data,
chunk_width,
chunk_height,
}
}
}
可能，当您使用world.chunk_width和world.chunk_height作为参数时，编译器不会将这些参数视为常量，然后实际生成除法和模运算。
另一方面，当您为这些参数提供常量时，它们可以在算法中传播（常量折叠）并且不执行一些昂贵的操作（除法、取模）（或转换为 bit-shifts/masks ).
Copying/pasting 您在 Godbolt（编译器资源管理器）中的代码，使 separate_test() 和 struct_test() public，并使用 -C opt-level=3 进行编译确认了这一点，因为 div 指令存在于 struct_test() 的生成代码中，但不存在于 separate_test().
我有函数 get_screen，它在 main.rs 的单独模块中指定。它需要两个 2D 向量（一个是 1920x1080，称为 screen，另一个更大，称为 world）并将 world 向量的一部分映射到 screen 向量。这是我第一次做的时候的函数签名：
pub fn get_screen(
screen: &mut Vec<Vec<[u8; 4]>>,
world: &Vec<Vec<Chunk>>,
camera_coords: (isize, isize),
screen_width: usize,
screen_height: usize,
chunk_width: usize,
chunk_height: usize,
)
我在执行时间上遇到了严重的问题，但我通过使用 #[inline].
然后我将 world 向量移动到它自己的结构中（连同一些其他相关变量，如块 width/height）并将 get_screen 函数变成新 world 结构。这是更改后的函数签名的样子：
pub fn get_screen(
&self,
screen: &mut Vec<Vec<[u8; 4]>>,
camera_coords: (isize, isize),
screen_width: usize,
screen_height: usize,
)
然后执行时间增加回 14 毫秒。我试过在 Cargo.toml 中启用 lto=true 并切换到 #[inline(always)] 来强制执行它，但编译器似乎拒绝像以前那样优化此功能。
我试图从结构中删除 get_screen 方法并 运行 它像以前一样作为自己的函数，这似乎修复了它，但是 只有 如果我不从结构中传递任何东西。如果我尝试将 usize 从 world 结构传递到单独的 get_screen 函数，则执行时间会从 3 毫秒增加回 14 毫秒。
举个例子来说明我的意思，如果我不直接从 world 结构传递任何内容，而是将 world 中的 2D 结构的克隆版本和硬编码的 chunk_width/chunk_height:
gen::get_screen(
&mut screen.buf,
&cloned_world_data,
camera_coords,
SCREEN_WIDTH,
SCREEN_HEIGHT,
CHUNK_WIDTH,
CHUNK_HEIGHT,
);
它在 3.3 毫秒内 运行 秒。当我直接从 world 结构传递 usize 字段 chunk_width/chunk_height 时：
gen::get_screen(
&mut screen.buf,
&cloned_world_data,
camera_coords,
SCREEN_WIDTH,
SCREEN_HEIGHT,
world.chunk_width,
world.chunk_height,
);
运行
需要 14.55 毫秒这里有什么？如何在使用我的 World 结构时让我的 get_screen 函数内联编译？最好我希望能够将它作为一种方法重新添加到我的 World 结构中，而不是将其分开。
这是一个最小的例子：
use std::time::Instant;
const SCREEN_HEIGHT: usize = 1080; //528;
const SCREEN_WIDTH: usize = 1920; //960;
const CHUNK_WIDTH: usize = 256;
const CHUNK_HEIGHT: usize = 256;
const GEN_RANGE: isize = 25; //how far out to gen chunks
fn main() {
let batch_size = 1_000;
struct_test(batch_size);
separate_test(batch_size);
}
fn struct_test(batch_size: u32) {
let world = World::new(CHUNK_WIDTH, CHUNK_HEIGHT, GEN_RANGE); //generate world
let mut screen = vec![vec!([0; 4]; SCREEN_WIDTH); SCREEN_HEIGHT];
let camera_coords: (isize, isize) = (0, 0); //set camera location
let start = Instant::now();
for _ in 0..batch_size {
get_screen(
&mut screen,
&world.data,
camera_coords,
SCREEN_WIDTH,
SCREEN_HEIGHT,
world.chunk_width,
world.chunk_height,
); //gets visible pixels from world as 2d vec
}
println!(
"struct: {:?} {:?}",
start.elapsed(),
start.elapsed() / batch_size
);
}
fn separate_test(batch_size: u32) {
let world = World::new(CHUNK_WIDTH, CHUNK_HEIGHT, GEN_RANGE); //generate world
let cloned_world_data = world.data.clone();
let mut screen = vec![vec!([0; 4]; SCREEN_WIDTH); SCREEN_HEIGHT];
let camera_coords: (isize, isize) = (0, 0); //set camera location
let start = Instant::now();
for _ in 0..batch_size {
get_screen(
&mut screen,
&cloned_world_data,
camera_coords,
SCREEN_WIDTH,
SCREEN_HEIGHT,
CHUNK_WIDTH,
CHUNK_HEIGHT,
); //gets visible pixels from world as 2d vec
}
println!(
"separate: {:?} {:?}",
start.elapsed(),
start.elapsed() / batch_size
);
}
///gets all visible pixels on screen relative camera position in world
#[inline(always)] //INLINE STOPPED WORKING??
pub fn get_screen(
screen: &mut Vec<Vec<[u8; 4]>>,
world: &Vec<Vec<Chunk>>,
camera_coords: (isize, isize),
screen_width: usize,
screen_height: usize,
chunk_width: usize,
chunk_height: usize,
) {
let camera = get_local_coords(&world, camera_coords, chunk_width, chunk_height); //gets loaded coords of camera in loaded chunks
(camera.1 - screen_height as isize / 2..camera.1 + screen_height as isize / 2)
.enumerate()
.for_each(|(py, y)| {
//for screen pixel index and particle in range of camera loaded y
let (cy, ly) = get_local_pair(y, chunk_height); //calculate chunk y and inner y from loaded y
if let Some(c_row) = world.get(cy) {
//if chunk row at loaded chunk y exists
(camera.0 - screen_width as isize / 2..camera.0 + screen_width as isize / 2)
.enumerate()
.for_each(|(px, x)| {
//for screen pixel index and particle in range of camera loaded x
let (cx, lx) = get_local_pair(x, chunk_width); //get loaded chunk x and inner x from loaded x
if let Some(c) = c_row.get(cx) {
screen[py][px] = c.data[ly][lx];
}
//if chunk in row then copy color of target particle in chunk
else {
screen[py][px] = [0; 4]
} //if target chunk doesn't exist color black
})
} else {
screen[py].iter_mut().for_each(|px| *px = [0; 4])
} //if target chunk row doesn't exist color row black
});
}
///calculates local coordinates in world vec from your global position
///returns negative if above/left of rendered area
pub fn get_local_coords(
world: &Vec<Vec<Chunk>>,
coords: (isize, isize),
chunk_width: usize,
chunk_height: usize,
) -> (isize, isize) {
let (wx, wy) = world[0][0].chunk_coords; //gets coords of first chunk in rendered vec
let lx = coords.0 - (wx * chunk_width as isize); //calculates local x coord based off world coords of first chunk
let ly = (wy * chunk_height as isize) - coords.1; //calculates local y coord based off world coords of first chunk
(lx, ly)
}
pub fn get_local_pair(coord: isize, chunk: usize) -> (usize, usize) {
(coord as usize / chunk, coord as usize % chunk)
}
///contains chunk data
#[derive(Clone)]
pub struct Chunk {
//world chunk object
pub chunk_coords: (isize, isize), //chunk coordinates
pub data: Vec<Vec<[u8; 4]>>, //chunk Particle data
}
impl Chunk {
///generates chunk
fn new(chunk_coords: (isize, isize), chunk_width: usize, chunk_height: usize) -> Self {
let data = vec![vec!([0; 4]; chunk_width); chunk_height];
Self { chunk_coords, data }
}
}
pub struct World {
pub data: Vec<Vec<Chunk>>,
pub chunk_width: usize,
pub chunk_height: usize,
}
impl World {
pub fn new(chunk_width: usize, chunk_height: usize, gen_range: isize) -> Self {
let mut data = Vec::new(); //creates empty vec to hold world
for (yi, world_chunk_y) in (gen_range * -1..gen_range + 1).rev().enumerate() {
//for y index, y in gen range counting down
data.push(Vec::new()); //push new row
for world_chunk_x in gen_range * -1..gen_range + 1 {
//for chunk in gen range of row
data[yi].push(Chunk::new(
(world_chunk_x, world_chunk_y),
chunk_width,
chunk_height,
)); //gen new chunk and put it there
}
}
Self {
data,
chunk_width,
chunk_height,
}
}
}
可能，当您使用world.chunk_width和world.chunk_height作为参数时，编译器不会将这些参数视为常量，然后实际生成除法和模运算。
另一方面，当您为这些参数提供常量时，它们可以在算法中传播（常量折叠）并且不执行一些昂贵的操作（除法、取模）（或转换为 bit-shifts/masks ).
Copying/pasting 您在 Godbolt（编译器资源管理器）中的代码，使 separate_test() 和 struct_test() public，并使用 -C opt-level=3 进行编译确认了这一点，因为 div 指令存在于 struct_test() 的生成代码中，但不存在于 separate_test().