Great article.Overclocking Intel's New 45nm QX9650: The Rules Have Changedhttp://www.anandtech.com/cpuchipsets/intel...aspx?i=3184&p=1

And here's the rule Anand believes has changed:http://www.anandtech.com/cpuchipsets/intel...aspx?i=3184&p=4Anandtech believes they are seeing a new Intel strategy of CPU throttling by skipping clock cycles. This reduces the amount of work done and therefore, heat. Since the work reduction occurs Before any heat event occurs, and . . . "If what we believe is true (see above), the implications could be enormous. The need for certain industries built on delivering high-performance cooling solutions to the overclocking community would be largely invalidated. What's the point in spending more money on a more effective heatsink if there's nothing to gain? With that said, we honestly believe a new direction in CPU overclocking may soon be upon us"(Anandtech).So (the argument might follow), if the actual work output will be the similar to a fully firing 4.2, why bother going to 4.7 with water or 5.7 with a $3K cascade? In any case, it appears the benefit of extreme O/Cs will no longer be linear.