Bill Todd (billtodd@metrocast.net) on 6/17/03 wrote:
---------------------------
>David Kanter (dkanter@realworldtech.com) on 6/17/03 wrote:
>---------------------------
>>Pau
>>l D
>>eMo
>>ne
>>has
>>j
>ust finished his latest article, entitled
>>Escape from the Planet of x86. This article deals with the history of
>>x86, the complexity introduced by the instruction set, as well as several attempts
>>to supplant x86 as the desktop architecture and a discussion of the theory that
>>IPF is intended to replace x86 on the desktop.
>
>The article does touch on at least two points I've noticed previously and meant to question:
>
>1. It once again alleges that a 1.3 GHz Madison/Deerfield will ship at relatively
>low power (60-something W is a figure I think Paul has mentioned at least once).
>Now, I do recall an article a while ago that stated that a 1.0 GHz 62 W. variant
>would be provided (with 1.5 MB of on-chip cache, though my impression is that the
>cache even when it's larger doesn't really soak up a large percentage of the total
>chip power), but that, combined with another reference I'm sure I've seen to Madison's
>peak power at 1.5 GHz being the same as McKinley's (130 W), makes a 1.3 GHz part
>at half that power seem a bit unrealistic.

If you read:
http://www.intel.com/design/itanium2/download/14_4_slides_r31_nsn.htm

and go to pag.24, you will note that Intel
don't have problem to lower power below 1.6-1.5Ghz.

If necessary, a 1.3Ghz 6MB model go at 1.1V and
likely even less with half L3.........


>2. There's also at least the suggestion that a 90 nm Itanic could appear some
>time next year. While that was the original schedule for 'Montecito' (before Montecito
>was redefined to be a dual-core chip), the last I knew Montecito was deferred to
>2005 and my impression was that the 9 MB Madison now planned for 2004 was a (very large) 130 nm device.

Yes but this is true? Or Intel will make a single core
0.09u cpu in the second half of 2004 and a double core
Montecito in 2005 ;)????

Alberto.