How does Duff's device work?

Question

I\'ve read the article on Wikipedia on the Duff\'s device, and I don\'t get it. I am really interested, but I\'ve read the explanation there a couple of times and I still do

Answer 1

Here is a working example for 64-bit memcpy with Duff's Device:

#include 
#include 

inline void __memcpy(void* to, const void* from, size_t count)
{
    size_t numIter = (count  + 56) / 64;  // gives the number of iterations;  bit shift actually, not division
    size_t rest = count & 63; // % 64
    size_t rest7 = rest&7;
    rest -= rest7;

    // Duff's device with zero case handled:
    switch (rest) 
    {
        case 0:  if (count < 8)
                     break;
                 do { *(((unsigned long long*&)to)++) = *(((unsigned long long*&)from)++);
        case 56:      *(((unsigned long long*&)to)++) = *(((unsigned long long*&)from)++);
        case 48:      *(((unsigned long long*&)to)++) = *(((unsigned long long*&)from)++);
        case 40:      *(((unsigned long long*&)to)++) = *(((unsigned long long*&)from)++);
        case 32:      *(((unsigned long long*&)to)++) = *(((unsigned long long*&)from)++);
        case 24:      *(((unsigned long long*&)to)++) = *(((unsigned long long*&)from)++);
        case 16:      *(((unsigned long long*&)to)++) = *(((unsigned long long*&)from)++);
        case 8:      *(((unsigned long long*&)to)++) = *(((unsigned long long*&)from)++);
                } while (--numIter > 0);
    }

    switch (rest7)
    {
        case 7: *(((unsigned char*)to)+6) = *(((unsigned char*)from)+6);
        case 6: *(((unsigned short*)to)+2) = *(((unsigned short*)from)+2); goto case4;
        case 5: *(((unsigned char*)to)+4) = *(((unsigned char*)from)+4);
        case 4: case4: *((unsigned long*)to) = *((unsigned long*)from); break; 
        case 3: *(((unsigned char*)to)+2) = *(((unsigned char*)from)+2);
        case 2: *((unsigned short*)to) = *((unsigned short*)from); break;
        case 1: *((unsigned char*)to) = *((unsigned char*)from);
    }
}

void main()
{
    static const size_t NUM = 1024;

    std::unique_ptr str1(new char[NUM+1]);  
    std::unique_ptr str2(new char[NUM+1]);

    for (size_t i = 0 ; i < NUM ; ++ i)
    {
        size_t idx = (i % 62);
        if (idx < 26)
            str1[i] = 'a' + idx;
        else
            if (idx < 52)
                str1[i] = 'A' + idx - 26;
            else
                str1[i] = '0' + idx - 52;
    }

    for (size_t i = 0 ; i < NUM ; ++ i)
    {
        memset(str2.get(), ' ', NUM); 
        __memcpy(str2.get(), str1.get(), i);
        if (memcmp(str1.get(), str2.get(), i) || str2[i] != ' ')
        {
            std::cout << "Test failed for i=" << i;
        }

    }

    return;
}

It handles zero-length case (in original Duff's Device there is assumption num>0). Function main() contains simple test cases for __memcpy.