I skimmed the Wikipedia article on AVX, but have no clue what it means. Care to go into a little more detail? Targeting the additional instructions will slow things down you think?
APL, as an array language, should, in theory at least, especially profit from automatic vectorization by the compiler. If the auto-vectorization works well, you get get a 4-16x speed-up for free (if you don't have data dependencies).