On Sun, 14 Oct 2001 [EMAIL PROTECTED] wrote:

> On 14 Oct 2001, at 7:30, Jean-Yves Canart wrote:
> 
> > According to latest benchmarks (http://www.mersenne.org/bench.htm),
> > AthlonXP seems to be slower than the Thunderbird.  Does anybody have a
> > technical explanation ?
> 
> The Athlon XP lies about its speed. Remember the old Cyrix trick? 

   In the benchmarks they appear to be sorted by MHz nonetheless. So
this is not a factor. There must be some other explanation.


[...]
> Having said all that, AFAIK the basic core of the Athlon XP is much 
> the same as the Thunderbird: it is fabbed at 0.13 microns instead 
> of 0.18 microns,

   Nope. It is still 0.18 microns (see Anandtech). If you have a source
claiming otherwise I would like to see it. They plan to switch to 0.13
early next year. Then, they should be able to increase the frequency big
time.


> which means keeping it cool should be a bit easier.

   They say it runs 20% cooler. It would probably run much cooler if
they had switched to 0.13 microns. The reason they provide for the lower
power consumption, is small architectural optimizations. But what I find
most interesting is its low power consumption when idle. They introduced
it for the laptop market but AFAIK it is also present in the regular
desktop processor.
   This poses a kind of dilemna since the energy used to run prime-net
is no longer energy that would have been wasted otherwise. So you have
to make a choice between preserving the environment and running
prime-net (to some extent).


[...]
> There is one small architecture change between Thunderbird and
> Athlon XP. Athlon XP now supports Intel SSE operations - but still
> not SSE2 as used in the Pentium 4. This probably doesn't help
> Prime95 since prefetch, which _is_ relevant, was already supported
> by all variants of Athlon CPUs.

   Well, they introduced other architectural improvements but none that
are relevant to prime-net: auto prefetch (prime-net uses explicit
prefetch), low power consumption when idle (i.e. when you're not running
prime-net), less fragile packaging, moderately useful thermal diode
(does not prevent the processor to burn when the heat sink falls).


> But it might be worth telling a system running Prime95 on an Athlon
> XP that it's actually running on a Pentium III just in case that's
> any faster than the native Athlon code.

   Why would it make more of a difference with the XP than with other
Athlons?


[...]
> Note particularly that e.g. 256 MB can be made up of one bank of 256
> MBit, two banks of 128 MBit or four banks of 64 MBit RAM chips;
> expect a performance difference of 5% - 7% between these
> configurations even if the chip access speeds & timings are
> identical. More banks are faster.

   Hmmm, you need to distinguish motherboards that merely have multiple
memory slots, from motherboards that have more than one data path to the
memory. The only motherboards that I know of that can do the latter are
some RDRAM based motherboards and the Nvidia nForce.
   In all other cases (the more common one?) putting multiple DIMMs
should not affect performance one way or another.


> > Do we have to consider now Intel/P4 as the best platform (at least for
> > prime95)?
> 
> For LL testing using mprime/Prime95:
> 
> That seems to have been the case for some months now; it's 
> SSE2 which makes the difference. A P4 running Prime95 is well 
> over twice as fast as a T'bird running at the same clock speed.
[...]

   Yes, AMD better implement SSE2 in their processors soon.


--
Francois Gouget         [EMAIL PROTECTED]        http://fgouget.free.fr/
                         Stolen from an Internet user:
              "f u cn rd ths, u cn gt a gd jb n cmptr prgrmmng !"

_________________________________________________________________________
Unsubscribe & list info -- http://www.scruz.net/~luke/signup.htm
Mersenne Prime FAQ      -- http://www.tasam.com/~lrwiman/FAQ-mers

Reply via email to