Re: hwcap supporting architectures?
On Tue, Jan 11, 2005 at 03:52:58PM +0900, GOTO Masanori wrote:
> Note that MMX will be removed from the next glibc 2.3.4 upload. It
> will provide only SSE2 (and CMOV, debian-specific for only VIA C3
Well, there's hand-crafted MMX code, so it's runtime checked. I guess
that would take care of it. After following the advice in other
replies, gcc is generating CMOVs, too.
> If you want to keep adding mmx, we may need discussion about this
> issue in future.
I think MMX is ok. I don't think gcc is generating MMX on its own.
> But nowadays many processors can use SSE2, so I guess changing cmov
> to SSE2 can fix the problem.
The SSE2 code generated by gcc causes clipping errors, so I turned that
> > My understanding is that this is also significant on sparc
> > (-mcpu=v9) and that this belongs in /usr/lib/v9. Is this right?
> Sparc defines HWCAP_SPARC_V9 and HWCAP_SPARC_ULTRA3. So v9 is right.
> See glibc sparc packages.
Where would ultra3 libs go? /usr/lib/sparc/ultra3? (sorry about the
naive question, but I had a hardtime finding this sort of
> > Mesa upstream uses -mcpu=ev5 -mieee on alpha. Is that ok? Where
> > does this belong into? /usr/lib/ev5?
> IIRC, alpha does not define any hwcaps.
Oh... I was looking at the atlas packages (I *think*), and it installed
some libs in /usr/lib/ev5 (or something along those lines). Is that
manually handled by atlas or something like that?
> > It also uses -mcpu=603 on powerpc. From my understanding this is
> > a lot hairier than other architectures since there's a whole load
> > more subarchitectures which are potentially incompatible with each
> > other.
> Powerpc does not define any hwcaps, too.
Thanks for the help!