Struct CachePadded 

pub struct CachePadded<T> { /* private fields */ }

A wrapper that pads a value to a 128-byte boundary to prevent false sharing.

False sharing occurs when two threads access different data that happens to reside on the same cache line, causing unnecessary cache invalidations. We use 128-byte alignment (two cache lines) because Intel’s L2 spatial prefetcher on Skylake+ fetches adjacent 64-byte line pairs, which can cause false sharing effects that 64-byte padding alone does not prevent.

Example

use laminar_core::tpc::CachePadded;
use std::sync::atomic::AtomicUsize;

// Each counter gets its own cache line pair
let counter1 = CachePadded::new(AtomicUsize::new(0));
let counter2 = CachePadded::new(AtomicUsize::new(0));

// Access the inner value
assert_eq!(counter1.load(std::sync::atomic::Ordering::Relaxed), 0);

Implementations

impl<T> CachePadded<T>

pub const fn new(value: T) -> Self

Creates a new cache-padded value.

pub const fn get(&self) -> &T

Returns a reference to the inner value.

pub fn get_mut(&mut self) -> &mut T

Returns a mutable reference to the inner value.

pub fn into_inner(self) -> T

Consumes the wrapper and returns the inner value.

Trait Implementations

impl<T: Clone> Clone for CachePadded<T>

fn clone(&self) -> Self

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl<T: Debug> Debug for CachePadded<T>

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

Formats the value using the given formatter.

impl<T: Default> Default for CachePadded<T>

fn default() -> Self

Returns the “default value” for a type.

impl<T> Deref for CachePadded<T>

type Target = T

The resulting type after dereferencing.

fn deref(&self) -> &Self::Target

Dereferences the value.

impl<T> DerefMut for CachePadded<T>

fn deref_mut(&mut self) -> &mut Self::Target

Mutably dereferences the value.

impl<T: Send> Send for CachePadded<T>

impl<T: Sync> Sync for CachePadded<T>