Re: About GCC optimizations

[uwe%stderr.spb.ru@localhost (Valeriy E. Ushakov)]

Joel CARNAT <joel%carnat.net@localhost> wrote:

> On Tue, Mar 11 2008 - 17:47, Valeriy E. Ushakov wrote:
> 
>> Having worked with people who do hardcoreperformance tuning as their
>> day job, one thing I've learned from them is that you probably
>> shouldn't even bother thinking about performance unless you measured
>> it and you understand specific conditions under which your system runs
>> and what kind of workloads you are optimizaing for.
>> 
>> So don't lose much time on this, you'll waste more time than any
>> improvements from highly fine-tuned -O* -f* are going to save you in
>> the few following years while the system you are optimizaing is still
>> useful. :) if -Os is what makes you feel good, just stick with it :)
> 
> heh, not that I particularily matter at all.

I'm sorry if that remark came across as a snub.  That's just something
I have to remind myself about when I get into "let's `optimize' it"
mood, so I though I might as well share it.  I didn't realize you had
those specific conditions and workloads you are optimizing for.


> maybe I'm taking it from the wrong side.
> but how to make sure that things that can be done on the hardware level
> is not done on the software level. I'm thinking of hardware to MPEG2
> decoding, or MMX/SSE CPU feature.

As was already suggested make sure your packages are built with those
features enabled if they provide such options.  If they do run-time
autodetection, make sure they do detect MMX/SSE.

Try both -O2 and -Os -freorder-blocks (i.e. -O2 sans -faling*) to see
if there's any difference.  


SY, Uwe
-- 
uwe%stderr.spb.ru@localhost                       |       Zu Grunde kommen
http://snark.ptc.spbu.ru/~uwe/          |       Ist zu Grunde gehen