WTF are you trying to nitpick? Are you one of the fools who reads "up to 20%" from an interview with an AMD exec, and think this means the IMC offers 20% performance boosts on general applications, or are you just trolling without reason?
I'll respond using two of your own statements: (Remember, the context in each is K8 performance vs. K7)
"The IMC is a wonderful contributer to performance on the K8, but it's not the primary one."
Sounds authoritative, yet you've been unable to substantiate your claim. Can you reference ANY document showing an "up to 20% gain" for any OTHER feature in the chip that is MORE applicable to the general case than low-latency memory access? I mean, you MIGHT have an argument re: SSE2 support, but that's hardly applicable to the "average" benchmark now, is it?
"The enhancement to the front end, SSE engine, execution pipeline, etc that I've mentioned before have a measurable contribution in the cases where the K8 is 30% ahead of the K7."
Can you be any more vague? (I doubt it.) "Measurable" contribution (of unknown magnitude) to a "30%" figure plucked out of thin air, to some unspecified or hypothetical benchmark. Surely someone who fights with such vigour on the topic should have some evidence to substantiate your claims?
Market Data 
Markets 
AI
