[ Thread Index |
Date Index
| More lists.liballeg.org/allegro-developers Archives
]
Quoting Eric Botcazou <ebotcazou@xxxxxxxxxx>:
> I simply wonder whether it wouldn't be better (performance-wise) to let
> the FPU do the multiplication instead of using the integer-based fixmul().
Hmm... Does that really make sense, given that part of the idea of using fixed
point is to allow fast fractional numbers on machines where floating point is
slower than integers? IMHO, it seems better to use the float datatype directly
if that is faster on the targetted machine. Also, I don't know for sure, but
isn't fixed/int <--> float conversion very slow?
Sven