lkml.org 
[lkml]   [2009]   [Nov]   [12]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
From
SubjectRe: i686 quirk for AMD Geode
Date
On Thu, 12 Nov 2009 13:18:05 +0100
Pavel Machek <pavel@ucw.cz> wrote:

> Hi!
>
> > > > The Geode NX (which no one has mentioned yet) is an Athlon
> > > > derived chip.
> > >
> > > *As far as I know* K6 didn't have NOPL, whereas K7 does.
> >
> > Which would be mroe indication that the Geode LX may in fact be a K6
> > based CPU design. The Geode NX is very clearly an Athlon (K7) and
> > AMD has never even tried to hide that. They have never said what
> > the LX is based on, other than it isn't based on the GX
> > (fortunately, that thing was a buggy piece of crap).
>
> Interesting...geode gx being buggy? I know pentium was famous for the
> fdiv bug, but never heard of geode gx problems...

http://www.amd.com/files/connectivitysolutions/geode/geode_gx/31533E_gx_2.1_specupdate.pdf

1.4 is my favorite. The branch prediction logic can send the
instruction pointer off to la-la land.

While at olpc, we had a sad discussion about what the *real* impact of
the workaround was...






\
 
 \ /
  Last update: 2009-11-13 03:07    [W:0.183 / U:3.752 seconds]
©2003-2017 Jasper Spaans. hosted at Digital OceanAdvertise on this site