跨核心記憶體成本

class OuterClassSlow
{
    struct InnerStruct
    {
        uint64_t threadOne;
        uint64_t threadTwo;
        uint64_t threadThree;
        uint64_t threadFour;
    };

    InnerStruct dataArray[1024];
};

class OuterClassFast
{
    uint64_t dataArrayThreadOne[1024];
    uint64_t dataArrayThreadTwo[1024];
    uint64_t dataArrayThreadThree[1024];
    uint64_t dataArrayThreadFour[1024];
};

for (uint64_t j = 0; j < params.iterations; j++)
{
    fred += *buffer + j;
}

mov         rcx,qword ptr [r8]  
add         rcx,rdx  
inc         rdx  
add         rdi,rcx  
cmp         rdx,r9  
jb          PerfRun::WorkerThreadRead+0D4h (07FF756A2E094h)  

for (uint64_t j = 0; j < params.iterations; j++)
{
    fred += buffer->load() + j;
}

mov         rax,qword ptr [rsi]  
add         rax,rcx  
inc         rcx  
add         rdi,rax  
cmp         rcx,rdx  
jb          PerfRun::WorkerThreadAtomicRead+0CFh (07FF756A2E4EFh)  

for (uint64_t j = 0; j < params.iterations; j++)
{
    *buffer = *buffer + 1;
}

mov         rcx,qword ptr [r8]  
inc         rcx  
mov         qword ptr [r8],rcx  
sub         rdx,1  
jne         PerfRun::WorkerThreadWrite+0D2h (07FF756A2E212h)  

for (uint64_t j = 0; j < params.iterations; j++)
{
    buffer->store(buffer->load() + 1);
}

mov         rcx,qword ptr [rdi]  
inc         rcx  
xchg        rcx,qword ptr [rdi]  
sub         rdx,1  
jne         PerfRun::WorkerThreadAtomicWrite+0CAh (07FF756A2E38Ah)  

for (uint64_t j = 0; j < params.iterations; j++)
{
    uint64_t temp = buffer->load();
    buffer->compare_exchange_strong(temp, temp + 1);
}

mov         rax,qword ptr [rdi]  
lea         rcx,[rax+1]  
lock cmpxchg qword ptr [rdi],rcx  
sub         rdx,1  
jne         PerfRun::WorkerThreadAtomicCAS+0CDh (07FF756A2E68Dh)