IPv4 주소를 문자열에서 정수로 변환하는 속도를 높이기 위해 벡터화 기술을 어떻게 사용할 수 있습니까?

UINT32 GetIP(const char *p)
{
    UINT32 dwIP=0,dwIP_Part=0;
    while(true)
    {
        if(p[0] == 0)
        {
            dwIP = (dwIP << 8) | dwIP_Part;
            break;
        }
        if(p[0]=='.') 
        {       
            dwIP = (dwIP << 8) | dwIP_Part;                     
            dwIP_Part = 0;
           p++;
        }
        dwIP_Part = (dwIP_Part*10)+(p[0]-'0');
        p++;
    }
    return dwIP;
}

UINT32 MyGetIP(const char *str) {
    // Load and convert input
    __m128i input = _mm_lddqu_si128((const __m128i*)str);
    input = _mm_sub_epi8(input, _mm_set1_epi8('0'));

    // Generate shuffled array
    __m128i cmp = input;
    UINT32 mask = _mm_movemask_epi8(cmp);
    __m128i shuf = shuffleTable[mask];
    __m128i arr = _mm_shuffle_epi8(input, shuf);

    // Calculate coefficients
    __m128i coeffs = _mm_set_epi8(0, 100, 10, 1, 0, 100, 10, 1, 0, 100, 10, 1, 0, 100, 10, 1);

    // Multiply and accumulate
    __m128i prod = _mm_maddubs_epi16(coeffs, arr);
    prod = _mm_hadd_epi16(prod, prod);

    // Reorder result
    __m128i imm = _mm_set_epi8(-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, 6, 4, 2, 0);
    prod = _mm_shuffle_epi8(prod, imm);

    // Extract result
    return _mm_extract_epi32(prod, 0);
}

void MyInit() {
    int len[4];
    for (len[0] = 1; len[0] <= 3; len[0]++)
        for (len[1] = 1; len[1] <= 3; len[1]++)
            for (len[2] = 1; len[2] <= 3; len[2]++)
                for (len[3] = 1; len[3] <= 3; len[3]++) {
                    int slen = len[0] + len[1] + len[2] + len[3] + 4;
                    int rem = 16 - slen;
                    for (int rmask = 0; rmask < 1<<rem; rmask++) {
                        int mask = 0;
                        char shuf[16] = {-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1};
                        int pos = 0;
                        for (int i = 0; i < 4; i++) {
                            for (int j = 0; j < len[i]; j++) {
                                shuf[(3-i) * 4 + (len[i]-1-j)] = pos;
                                pos++;
                            }
                            mask ^= (1<<pos);
                            pos++;
                        }
                        mask ^= (rmask<<slen);
                        _mm_store_si128(&amp;shuffleTable[mask], _mm_loadu_si128((__m128i*)shuf));
                    }
                }
}