Faster lookup tables using AVX2

I'm trying to speed up an algorithm which performs a series of lookup tables. I'd like to use SSE2 or AVX2. I've tried using the _mm256_i32gather_epi32 command but it is 31% slower. Does anyone have any suggestions to any improvements or a different approach?

Timings: C code = 234 Gathers = 340

static const int32_t g_tables[2][64];  // values between 0 and 63

template <int8_t which, class T>
static void lookup_data(int16_t * dst, T * src)
{
    const int32_t * lut = g_tables[which];

    // Leave this code for Broadwell or Skylake since it's 31% slower than C code
    // (gather is 12 for Haswell, 7 for Broadwell and 5 for Skylake)

#if 0
    if (sizeof(T) == sizeof(int16_t)) {
        __m256i avx0, avx1, avx2, avx3, avx4, avx5, avx6, avx7;
        __m128i sse0, sse1, sse2, sse3, sse4, sse5, sse6, sse7;
        __m256i mask = _mm256_set1_epi32(0xffff);

        avx0 = _mm256_loadu_si256((__m256i *)(lut));
        avx1 = _mm256_loadu_si256((__m256i *)(lut + 8));
        avx2 = _mm256_loadu_si256((__m256i *)(lut + 16));
        avx3 = _mm256_loadu_si256((__m256i *)(lut + 24));
        avx4 = _mm256_loadu_si256((__m256i *)(lut + 32));
        avx5 = _mm256_loadu_si256((__m256i *)(lut + 40));
        avx6 = _mm256_loadu_si256((__m256i *)(lut + 48));
        avx7 = _mm256_loadu_si256((__m256i *)(lut + 56));
        avx0 = _mm256_i32gather_epi32((int32_t *)(src), avx0, 2);
        avx1 = _mm256_i32gather_epi32((int32_t *)(src), avx1, 2);
        avx2 = _mm256_i32gather_epi32((int32_t *)(src), avx2, 2);
        avx3 = _mm256_i32gather_epi32((int32_t *)(src), avx3, 2);
        avx4 = _mm256_i32gather_epi32((int32_t *)(src), avx4, 2);
        avx5 = _mm256_i32gather_epi32((int32_t *)(src), avx5, 2);
        avx6 = _mm256_i32gather_epi32((int32_t *)(src), avx6, 2);
        avx7 = _mm256_i32gather_epi32((int32_t *)(src), avx7, 2);
        avx0 = _mm256_and_si256(avx0, mask);
        avx1 = _mm256_and_si256(avx1, mask);
        avx2 = _mm256_and_si256(avx2, mask);
        avx3 = _mm256_and_si256(avx3, mask);
        avx4 = _mm256_and_si256(avx4, mask);
        avx5 = _mm256_and_si256(avx5, mask);
        avx6 = _mm256_and_si256(avx6, mask);
        avx7 = _mm256_and_si256(avx7, mask);
        sse0 = _mm_packus_epi32(_mm256_castsi256_si128(avx0), _mm256_extracti128_si256(avx0, 1));
        sse1 = _mm_packus_epi32(_mm256_castsi256_si128(avx1), _mm256_extracti128_si256(avx1, 1));
        sse2 = _mm_packus_epi32(_mm256_castsi256_si128(avx2), _mm256_extracti128_si256(avx2, 1));
        sse3 = _mm_packus_epi32(_mm256_castsi256_si128(avx3), _mm256_extracti128_si256(avx3, 1));
        sse4 = _mm_packus_epi32(_mm256_castsi256_si128(avx4), _mm256_extracti128_si256(avx4, 1));
        sse5 = _mm_packus_epi32(_mm256_castsi256_si128(avx5), _mm256_extracti128_si256(avx5, 1));
        sse6 = _mm_packus_epi32(_mm256_castsi256_si128(avx6), _mm256_extracti128_si256(avx6, 1));
        sse7 = _mm_packus_epi32(_mm256_castsi256_si128(avx7), _mm256_extracti128_si256(avx7, 1));
        _mm_storeu_si128((__m128i *)(dst),      sse0);
        _mm_storeu_si128((__m128i *)(dst + 8),  sse1);
        _mm_storeu_si128((__m128i *)(dst + 16), sse2);
        _mm_storeu_si128((__m128i *)(dst + 24), sse3);
        _mm_storeu_si128((__m128i *)(dst + 32), sse4);
        _mm_storeu_si128((__m128i *)(dst + 40), sse5);
        _mm_storeu_si128((__m128i *)(dst + 48), sse6);
        _mm_storeu_si128((__m128i *)(dst + 56), sse7);
    }
    else
#endif
    {
        for (int32_t i = 0; i < 64; i += 4)
        {
            *dst++ = src[*lut++];
            *dst++ = src[*lut++];
            *dst++ = src[*lut++];
            *dst++ = src[*lut++];
        }
    }
}