Investigate gf2p8affineqb for the shuffle step

[aklomp]

This is a placeholder issue to make sure this gets noted somewhere.

It looks like the gf2p8affineqb instruction can do arbitrary bit permutations on 8-bit characters. This could be very interesting to implement the bit shifts needed by the encoders and decoders.

This instruction is only available on post-2019 Sunny Cove CPUs with GFNI extensions enabled.