How can I use SIMD to accelerate XOR two blocks of memory?

Question

I want to XOR two blocks of memory as quickly as possible, How can I use SIMD to accelerate it?

My original code is below:

void region_xor_w64(   uns         


        

Answer 1

As the size of the region is passed by value why wouldn't the code be:

void region_xor_w64(unsigned char *r1, unsigned char *r2, unsigned int i)
{
    while (i--)
        r2[i] = r1[i] ^ r2[i];
}

or even:

void region_xor_w64(unsigned char *r1, unsigned char *r2, unsigned int i)
{
    while (i--)
        r2[i] ^= r1[i];
}

If there's a preference towards going forwards ('up memory') and for using pointers, then:

void region_xor_w64(unsigned char *r1, unsigned char *r2, unsigned int i)
{
    while (i--)
        *r2++ ^= *r1++;
}