SSE的_mm_movemask_epi8在NEON的等效方法

参考链接：https://stackoverflow.com/questions/11870910/sse-mm-movemask-epi8-equivalent-method-for-arm-neon

int32_t _mm_movemask_epi8_neon(uint8x16_t input)
{
    const int8_t __attribute__ ((aligned (16))) xr[8] = {-7,-6,-5,-4,-3,-2,-1,0};
    uint8x8_t mask_and = vdup_n_u8(0x80);
    int8x8_t mask_shift = vld1_s8(xr);
    uint8x8_t lo = vget_low_u8(input);
    uint8x8_t hi = vget_high_u8(input);

    lo = vand_u8(lo, mask_and);
    lo = vshl_u8(lo, mask_shift);
    hi = vand_u8(hi, mask_and);
    hi = vshl_u8(hi, mask_shift);

    lo = vpadd_u8(lo,lo);
    lo = vpadd_u8(lo,lo);
    lo = vpadd_u8(lo,lo);

    hi = vpadd_u8(hi,hi);
    hi = vpadd_u8(hi,hi);
    hi = vpadd_u8(hi,hi);

    return ((hi[0] << 8) | (lo[0] & 0xFF));
}