static float L2SqrSIMD16Ext()

in cpp/src/Spaces/Euclidean.h [133:176]

• 36 lines of code
• 2 McCabe index (conditional complexity)

static float L2SqrSIMD16Ext(const float *pVect1, const float *pVect2,
                            const size_t qty) {
  float PORTABLE_ALIGN32 TmpRes[8];
  size_t qty16 = qty >> 4;

  const float *pEnd1 = pVect1 + (qty16 << 4);

  __m128 diff, v1, v2;
  __m128 sum = _mm_set1_ps(0);

  while (pVect1 < pEnd1) {
    //_mm_prefetch((char*)(pVect2 + 16), _MM_HINT_T0);
    v1 = _mm_loadu_ps(pVect1);
    pVect1 += 4;
    v2 = _mm_loadu_ps(pVect2);
    pVect2 += 4;
    diff = _mm_sub_ps(v1, v2);
    sum = _mm_add_ps(sum, _mm_mul_ps(diff, diff));

    v1 = _mm_loadu_ps(pVect1);
    pVect1 += 4;
    v2 = _mm_loadu_ps(pVect2);
    pVect2 += 4;
    diff = _mm_sub_ps(v1, v2);
    sum = _mm_add_ps(sum, _mm_mul_ps(diff, diff));

    v1 = _mm_loadu_ps(pVect1);
    pVect1 += 4;
    v2 = _mm_loadu_ps(pVect2);
    pVect2 += 4;
    diff = _mm_sub_ps(v1, v2);
    sum = _mm_add_ps(sum, _mm_mul_ps(diff, diff));

    v1 = _mm_loadu_ps(pVect1);
    pVect1 += 4;
    v2 = _mm_loadu_ps(pVect2);
    pVect2 += 4;
    diff = _mm_sub_ps(v1, v2);
    sum = _mm_add_ps(sum, _mm_mul_ps(diff, diff));
  }

  _mm_store_ps(TmpRes, sum);
  return TmpRes[0] + TmpRes[1] + TmpRes[2] + TmpRes[3];
}