奇怪的SIMD指令行为

SSE2指令(paddd xmm, m128)工作起来真的很奇怪。代码说明一切。

#include <iostream>
using namespace std;
int main()
{
     int * v0 = new int [80];
     for (int i=0; i<80; ++i)
          v0[i] = i;
     int * v1 = new int [80];
     for (int i=0; i<80; ++i)
          v1[i] = i;
     asm(
     ".intel_syntax noprefix;"
     "mov rcx , 20;"
     "mov rax , %0;"
     "mov rbx , %1;"
     "m_start:;"
     "cmp rcx , 0;"
     "je m_end;"
     "movdqu xmm0 , [rax];"
     "paddd xmm0 , [rbx];"
     "movdqu [rax] , xmm0;"
     "add rbx , 16;" /* WTF?? If I put there 128, it's work really bad */
     "add rax , 16;" /* but why?? I must add 128 because XMM width is 128 bits ... */
     "dec rcx;"
     "jmp m_start;"
     "m_end:;"
     ".att_syntax noprefix;"
     : //
     : "r"(v0) , "r"(v1)
     : //
     );
     for (int i=1; i<81; ++i)
     {
          cout << v0[i-1] << (char*)((i%10==0) ? "n" : ", ");
     }
     return 0;
}