Memory Model

Ordering strength (weakest to strongest):
Relaxed < Release/Acquire < AcqRel < SeqCst

Stronger ordering = more synchronization = more correct, but slower
Weaker ordering  = fewer barriers = faster, but needs careful analysis

#include <atomic>
#include <thread>

std::atomic<int> counter{0};
std::atomic<bool> ready{false};

// Producer thread
void producer() {
    data = 42;                              // (1) write data
    ready.store(true, std::memory_order_release);  // (2) signal
}

// Consumer thread
void consumer() {
    while (!ready.load(std::memory_order_acquire));  // (3) wait
    assert(data == 42);                              // (4) guaranteed to see (1)
}

Use case?
├── Counter (just needs atomicity, order irrelevant)    → Relaxed
├── Reference counting (decrement + final check)        → AcqRel (dec), Acquire (load 0 check)
├── Publish data from one thread to another             → Release (store), Acquire (load)
├── Mutual exclusion / mutex implementation             → AcqRel / SeqCst
├── Lock-free queue multiple producers/consumers        → SeqCst (safest to start)
└── Sequence number check (simple flag)                 → Release + Acquire

// Pattern 1: Spinlock
class Spinlock {
    std::atomic_flag flag = ATOMIC_FLAG_INIT;
public:
    void lock() {
        while (flag.test_and_set(std::memory_order_acquire))
            ; // spin
    }
    void unlock() {
        flag.clear(std::memory_order_release);
    }
};

// Pattern 2: Reference counting
class RefCounted {
    std::atomic<int> refcount{1};
public:
    void addref() {
        refcount.fetch_add(1, std::memory_order_relaxed);  // only need atomicity
    }
    void release() {
        if (refcount.fetch_sub(1, std::memory_order_acq_rel) == 1) {
            // AcqRel ensures we see all writes from other releasers
            delete this;
        }
    }
};

// Pattern 3: One-time initialisation
class LazyInit {
    std::atomic<void*> ptr{nullptr};
    std::mutex mtx;
public:
    void* get() {
        void* p = ptr.load(std::memory_order_acquire);
        if (p == nullptr) {
            std::lock_guard lock(mtx);
            p = ptr.load(std::memory_order_relaxed);
            if (p == nullptr) {
                p = create();
                ptr.store(p, std::memory_order_release);
            }
        }
        return p;
    }
};

use std::sync::atomic::{AtomicBool, AtomicUsize, Ordering};
use std::sync::Arc;

// Simple counter
let counter = Arc::new(AtomicUsize::new(0));

// Increment
counter.fetch_add(1, Ordering::Relaxed);

// Read
let val = counter.load(Ordering::Relaxed);

// Publish/subscribe pattern
static READY: AtomicBool = AtomicBool::new(false);

// Publisher thread
unsafe { DATA = 42; }  // Write data
READY.store(true, Ordering::Release);  // Signal

// Subscriber thread
while !READY.load(Ordering::Acquire) {}
let d = unsafe { DATA };  // Safe: guaranteed to see publisher's write

// C++ fence — equivalent to a global memory barrier
std::atomic_thread_fence(std::memory_order_acquire);  // Acquire fence
std::atomic_thread_fence(std::memory_order_release);  // Release fence

// Typical use: multiple atomic writes then one fence
relaxed_atomic_a.store(1, std::memory_order_relaxed);
relaxed_atomic_b.store(2, std::memory_order_relaxed);
std::atomic_thread_fence(std::memory_order_release);  // barrier for all above
sentinel.store(true, std::memory_order_relaxed);