// compliments of Adam Williams
#define ABSDIFF(frame1, frame2) \
({ \
 int result = 0; \
 asm volatile( \
  "mov %[result], #0\n"           /* accumulator */ \
 \
  "ldr r4, [%[src], #0]\n"        /* read data from address + offset*/ \
  "ldr r5, [%[dst], #0]\n" \
  "usada8 %[result], r4, r5, %[result]\n"      /* difference */ \
  "ldr r4, [%[src], #4]\n"        /* read data from address + offset */ \
  "ldr r5, [%[dst], #4]\n" \
  "usada8 %[result], r4, r5, %[result]\n"      /* difference */ \
 \
  "ldr r4, [%[src], #(64 * 1)]\n"        /* read data from address + offset*/ \
  "ldr r5, [%[dst], #(64 * 1)]\n" \
  "usada8 %[result], r4, r5, %[result]\n"      /* difference */ \
  "ldr r4, [%[src], #(64 * 1 + 4)]\n"        /* read data from address + offset */ \
  "ldr r5, [%[dst], #(64 * 1 + 4)]\n" \
  "usada8 %[result], r4, r5, %[result]\n"      /* difference */ \
 \
  "ldr r4, [%[src], #(64 * 2)]\n"        /* read data from address + offset*/ \
  "ldr r5, [%[dst], #(64 * 2)]\n" \
  "usada8 %[result], r4, r5, %[result]\n"      /* difference */ \
  "ldr r4, [%[src], #(64 * 2 + 4)]\n"        /* read data from address + offset */ \
  "ldr r5, [%[dst], #(64 * 2 + 4)]\n" \
  "usada8 %[result], r4, r5, %[result]\n"      /* difference */ \
 \
  "ldr r4, [%[src], #(64 * 3)]\n"        /* read data from address + offset*/ \
  "ldr r5, [%[dst], #(64 * 3)]\n" \
  "usada8 %[result], r4, r5, %[result]\n"      /* difference */ \
  "ldr r4, [%[src], #(64 * 3 + 4)]\n"        /* read data from address + offset */ \
  "ldr r5, [%[dst], #(64 * 3 + 4)]\n" \
  "usada8 %[result], r4, r5, %[result]\n"      /* difference */ \
 \
  "ldr r4, [%[src], #(64 * 4)]\n"        /* read data from address + offset*/ \
  "ldr r5, [%[dst], #(64 * 4)]\n" \
  "usada8 %[result], r4, r5, %[result]\n"      /* difference */ \
  "ldr r4, [%[src], #(64 * 4 + 4)]\n"        /* read data from address + offset */ \
  "ldr r5, [%[dst], #(64 * 4 + 4)]\n" \
  "usada8 %[result], r4, r5, %[result]\n"      /* difference */ \
 \
  "ldr r4, [%[src], #(64 * 5)]\n"        /* read data from address + offset*/ \
  "ldr r5, [%[dst], #(64 * 5)]\n" \
  "usada8 %[result], r4, r5, %[result]\n"      /* difference */ \
  "ldr r4, [%[src], #(64 * 5 + 4)]\n"        /* read data from address + offset */ \
  "ldr r5, [%[dst], #(64 * 5 + 4)]\n" \
  "usada8 %[result], r4, r5, %[result]\n"      /* difference */ \
 \
  "ldr r4, [%[src], #(64 * 6)]\n"        /* read data from address + offset*/ \
  "ldr r5, [%[dst], #(64 * 6)]\n" \
  "usada8 %[result], r4, r5, %[result]\n"      /* difference */ \
  "ldr r4, [%[src], #(64 * 6 + 4)]\n"        /* read data from address + offset */ \
  "ldr r5, [%[dst], #(64 * 6 + 4)]\n" \
  "usada8 %[result], r4, r5, %[result]\n"      /* difference */ \
 \
  "ldr r4, [%[src], #(64 * 7)]\n"        /* read data from address + offset*/ \
  "ldr r5, [%[dst], #(64 * 7)]\n" \
  "usada8 %[result], r4, r5, %[result]\n"      /* difference */ \
  "ldr r4, [%[src], #(64 * 7 + 4)]\n"        /* read data from address + offset */ \
  "ldr r5, [%[dst], #(64 * 7 + 4)]\n" \
  "usada8 %[result], r4, r5, %[result]\n"      /* difference */ \
 \
  : [result] "+r" (result) \
  : [src] "r" (frame1), [dst] "r" (frame2) \
  : "r4", "r5" \
  ); \
  \
 result; \

})

翻譯成C語言。

int absdiff(unsigned char *base1,unsigned char *base2)
{
    int result = 0;
    for(int i = 0;i <8;i++)
    {
        for(j = 0;j < 8;j++)
        {
            result += abs(base1[i*64 + j] - base2[i*64 + j]);
        }
    }
    return result;
}

其中usada8可以翻譯成。

int usada8(unsigned int base1,unsigned int base2,unsigned int base)
{
     unsigned char *p1 = (unsigned char *)&base1;
     unsigned char *p2 = (unsigned char *)&base2;
     for(int i = 0;i< 4;i++)
     {
         base += abs(*(p1 + i) - *(p2 + i));
     }

 /*  for(int i = 0;i< 4;i++)
    {
        //base += (unsigned char)abs((base1 >> 8*i)- (base2 >> 8*i));

    }*/
    return base;
}