Olaf van der Spek wrote:
On Apr 4, 2005 6:13 PM, Andrew P. <[EMAIL PROTECTED]> wrote:
Are you sure?
The s754 versions have an on die memory controller and a K8 core
(although with disabled 64-bit mode), which should make it
significantly faster then the K7 based Sempron on sA.
Yeah, it appears I got a wrong idea from some poor
article. As a matter of fact, Sempron/sA is based
on Barton core, while Sempron/s754 is a K8 sister.
The latter has an on-chip memory controller and
SSE2 instruction set supported. They are pretty
same in all other aspects though, and I still
suppose the perfomance margin is negligible.
Why do you expect so much performance to be lost compared to the Athlon 64 s754?
The Athlon 64 s754 is significantly faster than the Athlon XP.
I haven't seen any tests, yet I've seen Sempron/Socket-A
in action and it was impressive. I also have Athlon 64
and Athlon XP pc's at home and I don't think K8 is
so superior. In non-sse2 non-very-memory-intensive
applications it performs better, but not "turbo-charged".
Besides, AMD is pricing Socket-A Semprons even higher
than s754 versions. Considering the fact that s754 is
clocked lower than sA of the same PR, it can be hard
to determine the speed difference.
Anyway, I really think there's nothing for us to
argue about :) Gareth is staying with s754 and we
should be glad for him :)
Very best wishes,
Andrew P.
_______________________________________________
freebsd-questions@freebsd.org mailing list
http://lists.freebsd.org/mailman/listinfo/freebsd-questions
To unsubscribe, send any mail to "[EMAIL PROTECTED]"