Struct CachePadded 

pub struct CachePadded<T>(/* private fields */);

Wraps a value so it occupies a whole cache line, preventing the neighboring fields in a struct from being invalidated when the wrapped atomic is written by another core.

CachePadded<T> has the same size as T rounded up to the target’s cache-line size; for an AtomicUsize on x86_64 / AArch64 that means the wrapped value occupies 128 bytes total. Deref / DerefMut hide the padding from call sites so existing code reading padded.load(...) stays unchanged.

Example

use forge_alloc_core::CachePadded;
use core::sync::atomic::{AtomicUsize, Ordering};

struct Stats {
    hits: CachePadded<AtomicUsize>,
    misses: CachePadded<AtomicUsize>,
}

let s = Stats {
    hits: CachePadded::new(AtomicUsize::new(0)),
    misses: CachePadded::new(AtomicUsize::new(0)),
};
s.hits.fetch_add(1, Ordering::Relaxed);

Implementations

impl<T> CachePadded<T>

pub const fn new(v: T) -> CachePadded<T>

Wrap a value with cache-line alignment padding.

pub fn into_inner(self) -> T

Unwrap, returning the inner value.

Trait Implementations

impl<T> Debug for CachePadded<T>

where T: Debug,

fn fmt(&self, f: &mut Formatter<'_>) -> Result<(), Error>

Formats the value using the given formatter.

impl<T> Default for CachePadded<T>

where T: Default,

fn default() -> CachePadded<T>

Returns the “default value” for a type.

impl<T> Deref for CachePadded<T>

type Target = T

The resulting type after dereferencing.

fn deref(&self) -> &T

Dereferences the value.

impl<T> DerefMut for CachePadded<T>

fn deref_mut(&mut self) -> &mut T

Mutably dereferences the value.