1.5x faster ff_vorbis_floor1_render_list, 5% faster vorbis decoding on Core2. 1.3x and 3% on G4. Though I think only part of this speedup is due to my optimizations per se; some of it is that I got a better roll on the GCC random code generator. Trivial reorderings of this function have a disproportionate effect on speed.