While this application is silly, routing messages over mobile nodes
(cellular) is not. Of course, one needs nanoaccounting for packets
(bandwidth and battery resources is a scarce commodity) then.
Andrew Grove (InTeL) expects by 2011 dies to have
- 1 GTransistor complexity
- 1.8" die (ack!)
- 10 GHz clock
- 100 GIPS
- 0.07 um structures
After 8" wafers, 12" (30 cm!) wafer will be here soon. Great news for WSI.
While speaking of monster clocks: Daimler Benz (of all things) demonstrated
a Si/Ge heterobipolar transistor switching at 160 (!) GHz. Obviously, my
estimate of max 10 GHz was way too low, by at least one order of magnitude.
We should expect 100 GHz die clocks before long, which is wonderful news.
It seems, MMX multimedia instructions performance is distinctly inferior
to vanilla PowerPC.
ciao,
'gene
______________________________________________________________________________
|mailto:ui22204@sunmail.lrz-muenchen.de |transhumanism >H, cryonics, |
|mailto:Eugene.Leitl@uni-muenchen.de |nanotechnology, etc. etc. |
|mailto:c438@org.chemie.uni-muenchen.de |"deus ex machina, v.0.0.alpha" |
|icbmto:N 48 10'07'' E 011 33'53'' |http://www.lrz-muenchen.de/~ui22204 |