AVX2 で log2(__m256d) を効率的に実装するにはどうすればよいですか?

__m256d Log2(__m256d x) {
  // Extract exponent and adjust bias
  const __m256i exps64 = _mm256_srli_epi64(_mm256_and_si256(gDoubleExpMask, _mm256_castpd_si256(x)), 52);
  const __m256i exps32_avx = _mm256_permutevar8x32_epi32(exps64, gTo32bitExp);
  const __m128i exps32_sse = _mm256_castsi256_si128(exps32_avx);
  const __m128i normExps = _mm_sub_epi32(exps32_sse, gExpNormalizer);
  const __m256d expsPD = _mm256_cvtepi32_pd(normExps);

  // Prepare mantissa
  const __m256d y = _mm256_or_pd(_mm256_castsi256_pd(gDoubleExp0),
    _mm256_andnot_pd(_mm256_castsi256_pd(gDoubleExpMask), x));

  // Calculate t=(y-1)/(y+1) and t**2
  const __m256d tNum = _mm256_sub_pd(y, gVect1);
  const __m256d tDen = _mm256_add_pd(y, gVect1);
  const __m256d t = _mm256_div_pd(tNum, tDen);
  const __m256d t2 = _mm256_mul_pd(t, t); // t**2

  // Calculate terms and final log2
  const __m256d t3 = _mm256_mul_pd(t, t2); // t**3
  const __m256d terms01 = _mm256_fmadd_pd(gCoeff1, t3, t);
  const __m256d t5 = _mm256_mul_pd(t3, t2); // t**5
  const __m256d terms012 = _mm256_fmadd_pd(gCoeff2, t5, terms01);
  const __m256d t7 = _mm256_mul_pd(t5, t2); // t**7
  const __m256d terms0123 = _mm256_fmadd_pd(gCoeff3, t7, terms012);
  const __m256d t9 = _mm256_mul_pd(t7, t2); // t**9
  const __m256d terms01234 = _mm256_fmadd_pd(gCoeff4, t9, terms0123);
  const __m256d log2_y = _mm256_mul_pd(terms01234, gCommMul);
  const __m256d log2_x = _mm256_add_pd(log2_y, expsPD);

  return log2_x;
}