Sync with atomic variable

I am trying a very basic test with the atomic variable in c++:

this is a basic header:

#pragma once#include<atomic>class spinlock_mutex {  std::atomic_flag flag;public:  spinlock_mutex() : flag(ATOMIC_FLAG_INIT) {}  void lock() {    while (flag.test_and_set())      ;  }  void unlock() { flag.clear(); }};

Here is a very basic implementation of a queue which is on purpose oversized to contain all the samples:

template <class T, uint32_t MAX_SIZE = UCHAR_MAX>class SingleQueue {protected:  T _q[MAX_SIZE]{};  uint16_t _back {};  int16_t _front = 0;  uint16_t _count = 0;  spinlock_mutex mtx{};public:  SingleQueue() = default;  void push(T &&val) {    mtx.lock();    _q[_count] = std::move(val);    _count++;    mtx.unlock();  }  void push(T &val) {    mtx.lock();    _q[_count] = val;    _count++;    mtx.unlock();  }  void pop(T &val) {    mtx.lock();    val = _q[_count];    _back++;    mtx.unlock();  }

And this is my source code:

class DummyComm {public:  int l_val1{};  int l_val2{};};cu::SingleQueue<DummyComm,200000> q{};DummyComm val{};spinlock_mutex spin {};void producer_m() {  uint16_t count = 0;  for (int32_t idx = 0; idx < 100000; idx++) {    std::cout<<"Tx: "<<idx<<"\n";    q.push(DummyComm{idx,idx});  }}void consumer_m() {  std::vector<DummyComm> vec{};  DummyComm res {};  while(true)  {     q.pop(res);     std::cout<<"Rx: "<<res.l_val1<<"\n";     vec.push_back(res);     if(vec.back().l_val1==99999)     {        break;     }  }  std::cout<<vec.back().l_val1<<std::endl;}TEST(testOne, basic) {  std::thread prod{(producer_m)};  std::thread cons{(consumer_m)};  prod.join(), cons.join();}

I can't manage to store all the values I need in the array, it seems the reader is slower than the writer.

If I don't use an array but a single element to store the data, everything seems to go fine.

My understanding is that atomic variable should be updated at least on an x86 architecture (which I am currently using with g++ 9.4 on Linux), therefore count which is in a critical section between a lock/unlock of a spinlock should be updated.

Any word of advice? Thanks!