Instructions classification:
FP    : add, sub, mul, copy, par, arg
Maybe : and, or, xor, cmp(6)
Non FP: sdiv, udiv, srem, urem, store(4),
        load(7), ext(7), alloc(5), parc, argc, call

15 bits for operations  32768
-1 bit for s,d          16384

New conversion instructions:
 - Bitcast conversion between fp and ints. cast
 - Convert fp to/from int. convf convi (only signed at first, truncation)
 - Convert single to/from double convs convd

Summary:
	Add bitcast, convf convi, convs convd
	Add a 'floating point' bit to instructions