In the last episode (Jan 30), Yosi said:
> As the maintainer of the Lame spec files for Linux RPM packages, I'd
> like to ask for your help. I would like to use the best gcc (version
> 3.x) flags for differnet platforms. By "best" I mean the ones that
> produce the fastest code. Here are the values that I currently use
> for Pentium III or higher CPUs:
>
> -O3 -fomit-frame-pointer -mcpu=athlon -march=athlon \
> -malign-functions=4 -funroll-loops -fexpensive-optimizations \
> -fschedule-insns2 -mfancy-math-387 -pipe
>
> And these are the values I use when Lame is compiled on an Athlon:
>
> -O3 -fomit-frame-pointer -fno-strength-reduce -mcpu=athlon \
> -march=athlon -malign-functions=4 -funroll-loops \
> -fexpensive-optimizations -fschedule-insns2 -mfancy-math-387 -pipe
( putting on his Mr Pedantic hat )
-O2 and above implies -fexpensive-optimizations and -fschedule-insns2
(see code around line 4755 in toplev.c of gcc 3.0.3), so those two are
redundant.
Also note that -funroll-loops silently forces -fstrength-reduce (see
toplev.c:4936), so -fno-strength-reduce doesn't do anything either.
And last, -march=xxx implies -mcpu=xxx, so you don't need -mcpu.
--
Dan Nelson
[EMAIL PROTECTED]
_______________________________________________
mp3encoder mailing list
[EMAIL PROTECTED]
http://minnie.tuhs.org/mailman/listinfo/mp3encoder
