This whole trying to benchmark a user machine is fraught with difficulty
- things like preempt make it even more difficult.
For me, its tasks that can run for days where shaving a few hours off
the run time is useful, but not everyone does that. Unfortunately,
gentoo as a distro is particularly vulnerable to "use this and its
faster" and then its compared to something else and is found to be
slower on the numbers.
Unfortunately it has to come down to "if you haven't measured/compared
it, then it didn't happen." if you are going to recommend it to someone
else.
BillK
On Thu, 2003-10-23 at 12:48, Norberto Bensa wrote:
> Bill Kenworthy wrote:
> > For the reason that it is just a feeling: have you measured it, or is it
> > imagination?
>
> It feels faster and that's enough for me. You can't measure every day use in a
> reliable way: there're just too many variables. So, if it feels faster, it IS
> faster.
>
> Of course, everyone can test on their own if -Os if faster or slower than -O2.
> But what I can say for sure is: on a P3 box, -O3 is NOT faster than -O{s,2}
>
> Regards,
> Norberto
--
[EMAIL PROTECTED] mailing list
