Stroller <[EMAIL PROTECTED]> writes:
> On 29 Sep 2003, at 12:10 pm, Ulrich Rhein wrote:

>> gcc doesn't use SIMD instructions (except in very rare cases), because
>> it is hard for a compiler to use them. Additionally, gcc doesn't
>> generate much faster (just bigger) code when compiling with -march=...,
>> if it does generate different code at all. There is usually no
>> significiant performance gain with it.
> Why is Gentoo's ability to set CFLAGS optimisations in make.conf so
> widely touted, then..?

IMHO, people seem to have a strong belief in optimizing compilers in
general and that adoptions to a higher CPU type have great results. Even
the simple fact that gcc offers -march=-flags makes you think that they
have a noticeable effect. Additionally, if you have a distro that is
'perfectly adapted to your system', you have something more
individual...  It's more based on psychology than on facts.

> Surely if what you say is true, then this is a redundant feature of
> portage.

Not really, though. CFLAGS is only one part of the possible tweaks; for
instance you can simply try to link parts of the system statically
against the dietlibc instead of the glibc, which really does have
*massive* improvements: Statically linked supervise (in daemontools)
with 22k memory footprint. An *empty* process dynamically linked to the
glibc uses over 200k.

Uli
-- 
"Or have we eaten on the insane root,
 that takes the reason prisoner?"  -- MacBeth I, 3


--
[EMAIL PROTECTED] mailing list

Reply via email to