[EDIT]hmmm.....whats going on at AMD? (and history of 3Dfx Rampage)

[BoFox]

TPU did an analysis a while ago on GTX 480 (40nm):
https://www.techpowerup.com/reviews/Zota...on/27.html


Not too bad though, about 10W per 10 degree C difference, or 1W per 1C (TPU says 1.2W per 1C). 

But how about 30C difference...  would that still mean at least 20W power saving for a 14nm chip like RX 480?  I suppose that power leakage isn't as much of an issue with the more advanced lithography tech that did focus more on this area especially after it got bad during 40-45nm.  With much lower voltage, power leakage should be less of an issue, after all..  Oh well, still something to consider, I guess.

Idontcare posted this over at ATF:

Yeah the static power was marginally improved with 22nm over 32nm, not too surprising considering that with the node shrink all the dielectric insulating layers got thinner.

Ordinarily we would have expected leakage to get worse, not better, but the Finfets really helped with that.

What really saved 22nm from a static leakage perspective is that Intel was able to scale-down the voltage needed to hit any given clockspeed. (clockspeed is not a factor in static leakage, only temperature and voltage are factors in static leakage)

http://forums.anandtech.com/showpost.php...stcount=56

I noticed that power leakage was about half as bad at 22nm as with 45nm CPUs, which was interesting.

So, I'd like to be more modest with assumption about power leakage.  With RX 480's considerably lower voltage, I'd guess a more conservative ~10W power savings with 20C reduction in temperature compared to stock cooling.  A few posts above, I was saying "perhaps 20W or more" (for 25-30C reduction).  That does seem a bit far-fetched, so I'm not giving AMD's RX 480 that much credit, lol.  Thanks, Ocre!