C++ Threads Memory Order

atomic_thread_fence.cpp

#include <atomic>
#include <string>
#include <thread>
#include <iostream>
 
// Global
std::string computation(int a){
    return std::to_string(a);
}

void print(const std::string& val){
    std::cout << val << '\n';
}
 
std::atomic<int> arr[3] = {-1, -1, -1};
std::string data[1000]; //non-atomic data
 
// Thread A, compute 3 values.
void ThreadA(int v0, int v1, int v2)
{
//  assert(0 <= v0, v1, v2 < 1000);
    data[v0] = computation(v0);
    data[v1] = computation(v1);
    data[v2] = computation(v2);
    std::atomic_thread_fence(std::memory_order_release);
    std::atomic_store_explicit(&arr[0], v0, std::memory_order_relaxed);
    std::atomic_store_explicit(&arr[1], v1, std::memory_order_relaxed);
    std::atomic_store_explicit(&arr[2], v2, std::memory_order_relaxed);
}
 
// Thread B, prints between 0 and 3 values already computed.
void ThreadB()
{
    int v0 = std::atomic_load_explicit(&arr[0], std::memory_order_relaxed);
    int v1 = std::atomic_load_explicit(&arr[1], std::memory_order_relaxed);
    int v2 = std::atomic_load_explicit(&arr[2], std::memory_order_relaxed);
    std::atomic_thread_fence(std::memory_order_acquire);
//  v0, v1, v2 might turn out to be -1, some or all of them.
//  Otherwise it is safe to read the non-atomic data because of the fences:
    if (v0 != -1)
        print(data[v0]);
    if (v1 != -1)
        print(data[v1]);
    if (v2 != -1)
        print(data[v2]);
}
 
int main()
{
    std::thread a(ThreadA, 1 ,2 ,3);
    std::thread b(ThreadB);
    std::thread c(ThreadB);
    std::thread d(ThreadB);

    a.join(); b.join();
    c.join(); d.join();

    return 0;
}

memory_order_relaxed.cpp

#include <atomic>
#include <iostream>
#include <thread>
#include <vector>
 
std::atomic<int> cnt = {0};
 
void f()
{
    for (int n = 0; n < 1000; ++n)
        cnt.fetch_add(1, std::memory_order_relaxed);
}
 
int main()
{
    std::vector<std::thread> v;
    for (int n = 0; n < 10; ++n)
        v.emplace_back(f);
    for (auto& t : v)
        t.join();
    std::cout << "Final counter value is " << cnt << '\n';
}

memory_order_release_acquire.cpp

#include <atomic>
#include <cassert>
#include <string>
#include <thread>
 
std::atomic<std::string*> ptr;
int data;
 
void producer()
{
    std::string* p = new std::string("Hello");
    data = 42;
    ptr.store(p, std::memory_order_release);
}
 
void consumer()
{
    std::string* p2;
    while (!(p2 = ptr.load(std::memory_order_acquire)))
        ;
    assert(*p2 == "Hello"); // never fires
    assert(data == 42); // never fires
}
 
int main()
{
    std::thread t1(producer);
    std::thread t2(consumer);
    t1.join(); t2.join();
}

memory_order_release_acquire_2.cpp

#include <atomic>
#include <cassert>
#include <string>
#include <thread>
 
std::atomic<std::string*> ptr;
int data;
 
void producer()
{
    std::string* p = new std::string("Hello");
    data = 42;
    ptr.store(p, std::memory_order_release);
}
 
void consumer()
{
    std::string* p2;
    while (!(p2 = ptr.load(std::memory_order_acquire)))
        ;
    assert(*p2 == "Hello"); // never fires
    assert(data == 42); // never fires
}
 
int main()
{
    std::thread t1(producer);
    std::thread t2(consumer);
    t1.join(); t2.join();
}

memory_order_release_consume.cpp

#include <atomic>
#include <cassert>
#include <string>
#include <thread>
 
std::atomic<std::string*> ptr;
int data;
 
void producer()
{
    std::string* p = new std::string("Hello");
    data = 42;
    ptr.store(p, std::memory_order_release);
}
 
void consumer()
{
    std::string* p2;
    while (!(p2 = ptr.load(std::memory_order_consume)))
        ;
    assert(*p2 == "Hello"); // never fires: *p2 carries dependency from ptr
    assert(data == 42); // may or may not fire: data does not carry dependency from ptr
}
 
int main()
{
    std::thread t1(producer);
    std::thread t2(consumer);
    t1.join(); t2.join();
}

memory_order_seq_cst.cpp

#include <atomic>
#include <cassert>
#include <string>
#include <thread>
 
std::atomic<std::string*> ptr;
int data;
 
void producer()
{
    std::string* p = new std::string("Hello");
    data = 42;
    ptr.store(p, std::memory_order_release);
}
 
void consumer()
{
    std::string* p2;
    while (!(p2 = ptr.load(std::memory_order_consume)))
        ;
    assert(*p2 == "Hello"); // never fires: *p2 carries dependency from ptr
    assert(data == 42); // may or may not fire: data does not carry dependency from ptr
}
 
int main()
{
    std::thread t1(producer);
    std::thread t2(consumer);
    t1.join(); t2.join();
}

signal_fence.cpp

// https://stackoverflow.com/questions/14581090/how-to-correctly-use-stdatomic-signal-fence

#include <atomic>
#include <csignal>
#include <cassert>
#include <cstdlib>

// static_assert(2 == ATOMIC_INT_LOCK_FREE, "this implementation does not guarantee that std::atomic<int> is always lock free.");
static_assert(std::atomic<int>::is_always_lock_free, "this implementation does not guarantee that std::atomic<int> is always lock free.");


std::atomic<int> a = 0;
std::atomic<int> b = 0;

extern "C" void handler(int) {
    if (1 == a.load(std::memory_order_relaxed)) {
        std::atomic_signal_fence(std::memory_order_acquire);
        assert(1 == b.load(std::memory_order_relaxed));
    }

    std::exit(0);
}

int main() {
    std::signal(SIGTERM, &handler);

    b.store(1, std::memory_order_relaxed);
    std::atomic_signal_fence(std::memory_order_release);
    a.store(1, std::memory_order_relaxed);
    return 0;
}

thread_fence.cpp

// https://stackoverflow.com/questions/13632344/understanding-c11-memory-fences

#include <iostream>
#include <atomic>
#include <thread>

std::atomic<bool> flag(false);
int a;

void func1()
{
    a = 100;
    atomic_thread_fence(std::memory_order_release);
    flag.store(true, std::memory_order_relaxed);
}

void func2()
{
    while(!flag.load(std::memory_order_relaxed))
        ;

    atomic_thread_fence(std::memory_order_acquire);
    std::cout << a << '\n'; // guaranteed to print 100
}

int main()
{
    std::thread t1 (func1);
    std::thread t2 (func2);

    t1.join(); t2.join();
}


// Better
#include <iostream>
#include <atomic>
#include <thread>

std::atomic<bool> flag(false);
int a;

void func1()
{
    a = 100;
    atomic_thread_fence(std::memory_order_release);
    flag.store(true, std::memory_order_release);
}

void func2()
{
    while(!flag.load(std::memory_order_acquire))
        ;

    atomic_thread_fence(std::memory_order_acquire);
    std::cout << a << '\n'; // guaranteed to print 100
}

int main()
{
    std::thread t1 (func1);
    std::thread t2 (func2);

    t1.join(); t2.join();
}

thread_safe_memory_copy.cpp

// https://lemire.me/blog/2025/02/07/thread-safe-memory-copy/

void safe_memcpy(char *dest, const char *src, size_t count) {
  for (size_t i = 0; i < count; ++i) {
    char input =
        std::atomic_ref<const char>(src[i])
              .load(std::memory_order_relaxed);
    std::atomic_ref<char>(dest[i])
              .store(input, std::memory_order_relaxed);
  }
}

static_assert(std::atomic_ref<char>::required_alignment == 1);