Re: I follow this industry since 82, certainly there was always improvements towards the end of a node in this respect. But cutting the power within a node in half for a particular perfomance level is nothing I saw often.
You're forgetting that leakage is now a significant component to power, and at 90nm there is a much steeper trade-off between power and performance. In other words, by increasing performance a little, it comes at a more compromising trade-off to power. By shrinking the process and maintaining the same frequency, the lower power benefits will seem more distinct than they've been in the past.