为什么逐元素相加在分开的循环中比在一个合并的循环中快得多？

const int n = 100000;

for (int j = 0; j < n; j++) {
    a1[j] += b1[j];
    c1[j] += d1[j];
}

for (int j = 0; j < n; j++) {
    a1[j] += b1[j];
}

for (int j = 0; j < n; j++) {
    c1[j] += d1[j];
}

使用 Microsoft Visual C++ 10.0 进行完全优化和启用SSE2的32位编译，在 Intel Core 2 Duo (x64) 上，第一个示例需要5.5秒，而双循环示例仅需要1.9秒。

第一个循环的反汇编基本上如下所示（在完整程序中会重复出现约五次）：

movsd       xmm0,mmword ptr [edx+18h]
addsd       xmm0,mmword ptr [ecx+20h]
movsd       mmword ptr [ecx+20h],xmm0
movsd       xmm0,mmword ptr [esi+10h]
addsd       xmm0,mmword ptr [eax+30h]
movsd       mmword ptr [eax+30h],xmm0
movsd       xmm0,mmword ptr [edx+20h]
addsd       xmm0,mmword ptr [ecx+28h]
movsd       mmword ptr [ecx+28h],xmm0
movsd       xmm0,mmword ptr [esi+18h]
addsd       xmm0,mmword ptr [eax+38h]

双重循环示例的每个循环生成以下代码（以下块会重复大约三次）：

addsd       xmm0,mmword ptr [eax+28h]
movsd       mmword ptr [eax+28h],xmm0
movsd       xmm0,mmword ptr [ecx+20h]
addsd       xmm0,mmword ptr [eax+30h]
movsd       mmword ptr [eax+30h],xmm0
movsd       xmm0,mmword ptr [ecx+28h]
addsd       xmm0,mmword ptr [eax+38h]
movsd       mmword ptr [eax+38h],xmm0
movsd       xmm0,mmword ptr [ecx+30h]
addsd       xmm0,mmword ptr [eax+40h]
movsd       mmword ptr [eax+40h],xmm0

问题被证明与事实无关，因为行为严重取决于数组的大小（n）和CPU缓存。因此，如果有进一步的兴趣，我重新提出问题：

• 您能否对导致以下图表上的五个区域所示不同缓存行为的详细信息提供一些实质性的见解？

• 通过为这些CPU提供类似的图表，指出CPU/缓存架构之间的差异也可能很有趣。

以下是完整的代码。它使用TBB Tick_Count 进行更高分辨率的计时，可以通过不定义TBB_TIMING 宏来禁用：

#include <iostream>
#include <iomanip>
#include <cmath>
#include <string>

//#define TBB_TIMING

#ifdef TBB_TIMING   
#include <tbb/tick_count.h>
using tbb::tick_count;
#else
#include <time.h>
#endif

using namespace std;

//#define preallocate_memory new_cont

enum { new_cont, new_sep };

double *a1, *b1, *c1, *d1;


void allo(int cont, int n)
{
    switch(cont) {
      case new_cont:
        a1 = new double[n*4];
        b1 = a1 + n;
        c1 = b1 + n;
        d1 = c1 + n;
        break;
      case new_sep:
        a1 = new double[n];
        b1 = new double[n];
        c1 = new double[n];
        d1 = new double[n];
        break;
    }

    for (int i = 0; i < n; i++) {
        a1[i] = 1.0;
        d1[i] = 1.0;
        c1[i] = 1.0;
        b1[i] = 1.0;
    }
}

void ff(int cont)
{
    switch(cont){
      case new_sep:
        delete[] b1;
        delete[] c1;
        delete[] d1;
      case new_cont:
        delete[] a1;
    }
}

double plain(int n, int m, int cont, int loops)
{
#ifndef preallocate_memory
    allo(cont,n);
#endif

#ifdef TBB_TIMING   
    tick_count t0 = tick_count::now();
#else
    clock_t start = clock();
#endif
        
    if (loops == 1) {
        for (int i = 0; i < m; i++) {
            for (int j = 0; j < n; j++){
                a1[j] += b1[j];
                c1[j] += d1[j];
            }
        }
    } else {
        for (int i = 0; i < m; i++) {
            for (int j = 0; j < n; j++) {
                a1[j] += b1[j];
            }
            for (int j = 0; j < n; j++) {
                c1[j] += d1[j];
            }
        }
    }
    double ret;

#ifdef TBB_TIMING   
    tick_count t1 = tick_count::now();
    ret = 2.0*double(n)*double(m)/(t1-t0).seconds();
#else
    clock_t end = clock();
    ret = 2.0*double(n)*double(m)/(double)(end - start) *double(CLOCKS_PER_SEC);
#endif
    
#ifndef preallocate_memory
    ff(cont);
#endif

    return ret;
}


void main()
{   
    freopen("C:\\test.csv", "w", stdout);

    char *s = " ";

    string na[2] ={"new_cont", "new_sep"};

    cout << "n";

    for (int j = 0; j < 2; j++)
        for (int i = 1; i <= 2; i++)
#ifdef preallocate_memory
            cout << s << i << "_loops_" << na[preallocate_memory];
#else
            cout << s << i << "_loops_" << na[j];
#endif
            
    cout << endl;

    long long nmax = 1000000;

#ifdef preallocate_memory
    allo(preallocate_memory, nmax);
#endif
    
    for (long long n = 1L; n < nmax; n = max(n+1, long long(n*1.2)))
    {
        const long long m = 10000000/n;
        cout << n;

        for (int j = 0; j < 2; j++)
            for (int i = 1; i <= 2; i++)
                cout << s << plain(n, m, j, i);
        cout << endl;
    }
}