在C ++中缓存，出了什么问题？

Question

在以下代码中，为什么f2()比f1()更快？

const int n = 3;
const int m = 4096;

void f1()
{
    int mas[n][m];
    //int mas_1[n][m];
    for (int i = 0; i < n; ++i)
    {
        for (int i_1 = 0; i_1 < m; ++i_1)
        {
            mas[i][i_1] = 1;
            //mas_1[i][i_1] = 1;
        }
    }
}

void f2()
{
    int mas[n][m];
    //int mas_1[n][m];
    for (int i = 0; i < m; ++i)
    {
        for (int i_1 = 0; i_1 < n; ++i_1)
        {
            mas[i_1][i] = 1;
            //mas_1[i_1][i] = 1;
        }
    }
}
int main()
{
    for (size_t a = 0; a < 10; ++a)
    {
        {
            clock_t s = clock();
            for (size_t i = 0; i < 10000; ++i)
            {
                f1();
            }
            clock_t e = clock();
            printf("T1: %d\n", e - s);
        }
        {
            clock_t s = clock();
            for (size_t i = 0; i < 10000; ++i)
            {
                f2();
            }
            clock_t e = clock();
            printf("T2: %d\n", e - s);
        }
    }
}

优化是禁用，x64版本 我知道缓存，但为什么它不能在这里工作...
//当n大于N时，f1()比f2()更快 //我有i5 HQ4750 2ghz，8mb缓存