RBW wrote:
At 500 gigahertz, the technology is 250 times faster than chips in
today's cellphones, which operate at 2 gigahertz. At room temperature,
the chips operate at 350 gigahertz, far faster than other chips in
commercial use today."
http://www.nytimes.com/2006/06/20/technology/20chip.html?ei=5090&en=215511bacfc970b5&ex=1308456000&partner=rssuserland&emc=rss&pagewanted=print
*(http://tinyurl.com/g26bu)
*That 12-24 months statement seems a bit fantastic from our current,
<cough>bullshit<cough>
350 GHz transistors are not that unusual. The ft on your pedestrain
cell phone silicon bipolar transistors is probably around 200GHz.
The problem is all the stuff *around* that transistor.
The current issue in semiconductors is *not* raw speed. We are fast
enough for almost everything we need to do. If speed were an issue,
everybody would be all sitting in TSMC's fastest process. They are not.
Most people are a generation or two behind.
The issues currently are power and density. The flash people have a
tough time getting the speed they need *and* the density they need. The
microprocessor people have trouble getting the speed they need *and* the
power consumption they need (too high, obviously, not too low).
Somehow it seems that the water cooled CPU attachments are about to go
through some radical transformationa...
http://www.overclockers.com/articles671/
Doubtful. Even with the heat consumption of modern chips, the
reliability drop from having that mechanical part is large and
catastrophic ie. everybody knows who and how to pin the blame when the
part fails.
-a
--
[email protected]
http://www.kernel-panic.org/cgi-bin/mailman/listinfo/kplug-list
