Struct CacheAlign

#[repr(align(128))]
pub struct CacheAlign<T> { /* private fields */ }

Aligns and pads a value to the length of a cache line.

In concurrent programming, sometimes it is desirable to make sure commonly accessed pieces of data are not placed into the same cache line. Updating an atomic value invalidates the whole cache line it belongs to, which makes the next access to the same cache line slower for other CPU cores. Use CacheAlign to ensure updating one piece of data doesn’t invalidate other cached data.

Size and alignment

Cache lines are assumed to be N bytes long, depending on the architecture:

• On x86-64, aarch64, and powerpc64, N = 128.
• On arm, mips, mips64, sparc, and hexagon, N = 32.
• On m68k, N = 16.
• On s390x, N = 256.
• On all others, N = 64.

Note that N is just a reasonable guess and is not guaranteed to match the actual cache line length of the machine the program is running on. On modern Intel architectures, spatial prefetcher is pulling pairs of 64-byte cache lines at a time, so we pessimistically assume that cache lines are 128 bytes long.

The size of CacheAlign<T> is the smallest multiple of N bytes large enough to accommodate a value of type T.

The alignment of CacheAlign<T> is the maximum of N bytes and the alignment of T.

Examples

Alignment and padding:

let array = [CacheAlign::new(1i8), CacheAlign::new(2i8)];
let addr1 = &*array[0] as *const i8 as usize;
let addr2 = &*array[1] as *const i8 as usize;

assert!(addr2 - addr1 >= 32);
assert_eq!(addr1 % 32, 0);
assert_eq!(addr2 % 32, 0);

When building a concurrent queue with a head and a tail index, it is wise to place them in different cache lines so that concurrent threads pushing and popping elements don’t invalidate each other’s cache lines:

struct Queue<T> {
    head: CacheAlign<AtomicUsize>,
    tail: CacheAlign<AtomicUsize>,
    buffer: *mut T,
}

Implementations

impl<T> CacheAlign<T>

pub const ALIGN: usize

The alignment of a cache line in the current platform.

pub const fn new(t: T) -> CacheAlign<T>

Pads and aligns a value to the length of a cache line.

Examples

let padded_value = CacheAlign::new(1);

pub fn into_inner(self) -> T

Returns the inner value.

Examples

let padded_value = CacheAlign::new(7);
let value = padded_value.into_inner();
assert_eq!(value, 7);

pub const fn into_inner_copy(self) -> T

where Self: Copy,

Returns the copied inner value in compile-time.

Trait Implementations

impl<T: Clone> Clone for CacheAlign<T>

fn clone(&self) -> CacheAlign<T>

Returns a copy of the value.

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

Performs copy-assignment from source.

impl<T: Debug> Debug for CacheAlign<T>

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

Formats the value using the given formatter.

impl<T: Default> Default for CacheAlign<T>

fn default() -> CacheAlign<T>

Returns the “default value” for a type.

impl<T> Deref for CacheAlign<T>

type Target = T

The resulting type after dereferencing.

fn deref(&self) -> &T

Dereferences the value.

impl<T> DerefMut for CacheAlign<T>

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

Mutably dereferences the value.

impl<T: Display> Display for CacheAlign<T>

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

Formats the value using the given formatter.

impl<T> From<T> for CacheAlign<T>

fn from(t: T) -> Self

Converts to this type from the input type.

impl<T: Hash> Hash for CacheAlign<T>

fn hash<__H: Hasher>(&self, state: &mut __H)

Feeds this value into the given Hasher.

fn hash_slice<H>(data: &[Self], state: &mut H)

where H: Hasher, Self: Sized,

Feeds a slice of this type into the given Hasher.

impl<T: PartialEq> PartialEq for CacheAlign<T>

fn eq(&self, other: &CacheAlign<T>) -> bool

Tests for self and other values to be equal, and is used by ==.

fn ne(&self, other: &Rhs) -> bool

Tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

impl<T: Copy> Copy for CacheAlign<T>

impl<T: Eq> Eq for CacheAlign<T>

impl<T: Send> Send for CacheAlign<T>

Available on crate feature unsafe_sync only.

impl<T> StructuralPartialEq for CacheAlign<T>

impl<T: Sync> Sync for CacheAlign<T>

Available on crate feature unsafe_sync only.