The update of atomic variables is more expensive than regular primitives

#include <memory>

using namespace std::chrono;
using shared_ptr_t=std::shared_ptr<int>;

void shared_ptr_receiver_by_value(shared_ptr_t ptr) {
    (void)*ptr;
}

void shared_ptr_receiver_by_ref(const shared_ptr_t& ptr) {
    (void)*ptr;
}

void test_copy_by_value(uint64_t n) {
    auto ptr = std::make_shared<int>(100);
    for(uint64_t i = 0u; i < n; ++i) {
        shared_ptr_receiver_by_value(ptr);
    }
}

void test_copy_by_ref(uint64_t n) {
    auto ptr = std::make_shared<int>(100);
    for(uint64_t i = 0u; i < n; ++i) {
        shared_ptr_receiver_by_ref(ptr);
    }
}

int main(int argc, char *argv[]) {
    uint64_t n = (argc == 3 ) ? std::stoull(argv[2]) : 100;
    auto t1 = high_resolution_clock::now();
    if(atoi(argv[1]) == 1) {
        test_copy_by_value(n);
    } else {
        test_copy_by_ref(n);
    }
    auto t2 = high_resolution_clock::now();
    auto time_span = duration_cast<duration<int64_t, std::micro>>(t2 - t1);
    std::cout << "It took me " << time_span.count() << " microseconds.\\n";
    return 0;
}

$ ./cpu_atomic_copy.bin 1 999999
It took me 3616 microseconds.
$ ./cpu_atomic_copy.bin 2 999999
It took me 2 microseconds.