使用 SSE 计算到多个字符串的汉明距离

Question

我有 n(8 位)个字符串，它们的长度都相同(比如 m)，另一个字符串 s同样的长度。我需要计算从 s 到每个其他字符串的汉明距离。在普通的 C 中，类似于:

unsigned char strings[n][m];
unsigned char s[m];
int distances[n];

for(i=0; i<n; i++) {
  int distances[i] = 0;
  for(j=0; j<m; j++) {
    if(strings[i][j] != s[j])
      distances[i]++;
  }
}

我想在 gcc 中使用 SIMD 指令来更有效地执行此类计算。我读过 SSE 4.2 中的 PcmpIstrI 很有用，我的目标计算机支持该指令集，所以我更喜欢使用 SSE 4.2 的解决方案。

编辑:

我编写了以下函数来计算两个字符串之间的汉明距离:

static inline int popcnt128(__m128i n) {
  const __m128i n_hi = _mm_unpackhi_epi64(n, n);
  return _mm_popcnt_u64(_mm_cvtsi128_si64(n)) + _mm_popcnt_u64(_mm_cvtsi128_si64(n_hi));
}

int HammingDist(const unsigned char *p1, unsigned const char *p2, const int len) {
#define MODE (_SIDD_UBYTE_OPS | _SIDD_CMP_EQUAL_EACH | _SIDD_BIT_MASK | _SIDD_NEGATIVE_POLARITY)
  __m128i smm1 = _mm_loadu_si128 ((__m128i*) p1);
  __m128i smm2 = _mm_loadu_si128 ((__m128i*) p2);
  __m128i ResultMask;

  int iters = len / 16;
  int diffs = 0;
  int i;

  for(i=0; i<iters; i++) {
    ResultMask = _mm_cmpestrm (smm1,16,smm2,16,MODE); 

    diffs += popcnt128(ResultMask);
    p1 = p1+16;
    p2 = p2+16;
    smm1 = _mm_loadu_si128 ((__m128i*)p1);
    smm2 =_mm_loadu_si128 ((__m128i*)p2);
  }

  int mod = len % 16;
  if(mod>0) {
     ResultMask = _mm_cmpestrm (smm1,mod,smm2,mod,MODE); 
     diffs += popcnt128(ResultMask);
  }

  return diffs;
} 

所以我可以通过以下方式解决我的问题:

for(i=0; i<n; i++) {
  int distances[i] = HammingDist(s, strings[i], m);
}

这是我能做的最好的，还是我可以利用所比较的字符串之一始终相同这一事实？此外，我是否应该对阵列进行一些对齐以提高性能？

另一次尝试

根据哈罗德的推荐，我编写了以下代码:

void _SSE_hammingDistances(const ByteP str, const ByteP strings, int *ds, const int n, const int m) {
    int iters = m / 16;

    __m128i *smm1, *smm2, diffs;

    for(int j=0; j<n; j++) {
        smm1 = (__m128i*)  str;
        smm2 = (__m128i*)  &strings[j*(m+1)]; // m+1, as strings are '\0' terminated

        diffs =  _mm_setzero_si128();

        for (int i = 0; i < iters; i++) {
            diffs = _mm_add_epi8(diffs, _mm_cmpeq_epi8(*smm1, *smm2));
            smm1 += 1;
            smm2 += 1;
        }

        int s = m;
        signed char *ptr = (signed char *) &diffs;
        for(int p=0; p<16; p++) {
            s += *ptr;
            ptr++;
        }

        *ds = s;
        ds++;
    }
}

但我无法使用 psadbw 在 __m128i 中最后添加字节。谁能帮我解决这个问题？

Answer 1

这是您最新例程的改进版本，它使用 PSADBW (_mm_sad_epu8) 来消除标量代码:

void hammingDistances_SSE(const uint8_t * str, const uint8_t * strings, int * const ds, const int n, const int m)
{
    const int iters = m / 16;

    const __m128i smm1 = _mm_loadu_si128((__m128i*)str);

    assert((m & 15) == 0);      // m must be a multiple of 16

    for (int j = 0; j < n; j++)
    {
        __m128i smm2 = _mm_loadu_si128((__m128i*)&strings[j*(m+1)]); // m+1, as strings are '\0' terminated

        __m128i diffs = _mm_setzero_si128();

        for (int i = 0; i < iters; i++)
        {
            diffs = _mm_sub_epi8(diffs, _mm_cmpeq_epi8(smm1, smm2));
        }

        diffs = _mm_sad_epu8(diffs, _mm_setzero_si128());
        ds[j] = m - (_mm_extract_epi16(diffs, 0) + _mm_extract_epi16(diffs, 4));
    }
}