Replaces {E,G,M}d_q with {E,G,M}y. The 'y' code matches what Intel uses for OPSZ_4_rex8; matches our existing {B,E,G,R}y codes; and conforms to the convention that an underscore between two size letters indicates a partial size out of a larger whole.
Renames the F{x,y,z} codes used for particular floating-point sizes to Ff{x,y,z}, to avoid confusion with Intel's 'x', 'y', and 'z' size codes.