Advanced Micro Devices Inc (AMD)

[fastpathguru]

So you accept groo's prediction that K8L will be Q1'08, but dismiss his prediction that revG QC will have superior performance vs. Intel's QC...

100% pro-Intel selectivity. Hmmm.

So now Intel only has a 2 quarter lead in the ultra high end,

Ultra-high-end of what? A double-die Intel QC part will be very expensive... It will be competing with 4x4/2S/4S AMD machines and Intel's own 2S machines, hamstrung by a single FSB's bandwidth.

and they'll still be faster than AMD in everything else through next year.

And by the way, I don't buy Charlie's "Elephant drinking through a straw" metaphor for Clovertown. Memory bandwidth means a lot in workstation apps, but as tests have already shown, Opteron has scores more memory bandwidth than Woodcrest and still loses in the vast majority of apps.

2x the cores will place 2x the demand on memory bandwidth. We know (and you just stated) AM2 has tons of memory bandwidth overhead... Does CMW? Could it be that with QC, AM2 begins to utilize the overhead while CMW is already near saturation at DC and the FSB becomes a bottleneck at QC? (That is the scenario groo is predicting and it is not contradicted your argument.) QC is going to be used primarily in servers... And servers live or die on bandwidth.

fpg