I've heard that the main problem is that they don't really have the expertise and manpower anymore to do a full custom design, but are using a more ASIC style process - influenced by the ATI folks. Also, this is an all-new architecture and so you'd expect that it would be unpolished and untuned. Intel hasn't done anything as drastic as what AMD has done here since the introduction of the Pentium Pro. Well, there was the Atom but Bobcat (also an all new design) is able to beat that the same way that Intel is beating AMD at the high end.

In theory, this will let AMD mix and match components easily, and quickly synthesize new designs with the right mix of Bulldozer cores, Bobcat cores, GPU cores, memeory controllers, etc to meet market demand. I haven't seen any evidence that this is actually happening, though, or that its worth the price. By contrast, Intel has huge design teams that can afford to hand tune a range of designs to changing circumstances.

Its also true that though GF has a more tolerant set of design rules in its 32nm process, it pays for it in lower overall performance compared to Intel's process at the same node.

I'm not sure the high frequency design was a kiss of death. In terms of pipelining it doesn't seem any more aggressive than the Power7, which has been very successful. The Power7 benefits from 4-way SMT, though, and that probably helps hide the cache latency that is hurting Bulldozer so much.

EDIT: See example here: http://realworldtech.com/forums/index.cfm?action=detail&...