[Pc_Support] (no subject)

[ed]

On Fri, 30 Dec 2005 12:27:18 -0500
"Damien McKenna" <dmckenna at thelimucompany.com> wrote:

> Page 3 has a great quote:
> "Intel's architecture, featuring no on-die memory controller, allows
> for such a split to be made without any major changes.  Even on
> Smithfield, all traffic between the cores actually had to travel out
> one core, off the chip and onto the external FSB and then back into
> the other core. With Presler, the same type of communication can take
> place without any disruptions, the only difference is that the data
> from core to core has a slightly longer distance to travel."
> 
> Aweful, simply aweful.
> 
> You can strap a rocket to a turd but its still a turd :o)

I think it's part of the master plan to have 32 cores on a single chip,
think of it as network protocol. Sure, its better to have a SCSI cable
between computers, but that's just not workable over any distance.

Well, that's my 20pence that I read into it.

-- 
Regards, Ed http://www.usenix.org.uk - http://irc.is-cool.net 
:%s/Open Source/Free Software/g