Re: Intel Core2Duo (T7400)
On Thu, Nov 08, 2007 at 10:31:56AM +0100, Bernd Petrovitsch wrote:
> ACK - in theory.
> ACK - and since that software (also) needs to be fixed. Therefor I'm
> counting this in practice as an non-issue.
I don't consider it a real issue either, but it is still something. I
am not sure why sparc tends to run 32bit for most programs and only
64bit for select cases where it helps. Certainly x86_64 seems to be
better than i386 in just about all cases.
> Hmm, any better numbers on it (or links to places with them)?
Well toms hardware had a test of the new intel 45nm quad core certainly
showed that for memory bandwidth even the slowest AMD has quite a bit
more bandwidth than the brand new top of the line intel. And that's for
single socket. Every time you add a socket to an AMD server you get
another complete memory controller with bandwidth, while on an intel
system you get another cpu trying to use your existing front side bus
bandwidth. This is probably the main reason the opterons scale past 2
socket systems and xeons do not. In a couple of years when intel gets
their new interconnect implemented AMD will have a very big problem,
which is rather unfortunate. I hope they come out with a way faster
improved CPU before then.
> On FC6 (IIRC) it took >80 i386 RPMS just to install OOorg.
> The problem is not really the disk space for it (or the time and
> resources OOorg needs to start) but that `yum upgrade` also pulls new
> i386 packages which are not realy needed on the next update just because
> the x86_64 version is upgraded. So unless you cleanup regularly you end
> up with all of them (or you ignore "i386" in yum.conf and temporarily
> add it if some dependency lib of OOorg wants to be updated - which is
> awkward too).
I don't deal with RPM based systems anymore. I stopped doing that when
RH6.0 kept crashing bind multiple times a day. :)
> That reminds me of a TYAN mainboard (Toledo i3100/S5207, Intel E6600 CPU
> on it IIRC, Ubuntu + self-compiled kernel on it IIRC) bought in
> March 2007 which ran fine with 4GB but didn't even boot with 8GB RAM
> (and RAM is on their "recommend RAM" list for that board) and stopped
> with an BIOS error not mentioned in the manual.
> The third BIOS update - to a "beta" version - (since March) seems to
> make it work now.
You would think board makers SHOULD test the bios with every OS out
there not just the most popular one. Even testing with 64bit vista and
the ram maxed out on the board would catch many bugs (like the MTRR bugs
in intel bioses on the majority of their current boards).