Intel Core 2 Extreme X6800 Preview from Taiwan

[Yousuf Khan]

You really seem to be twisting things around to try and support your view.
Apparently, a 3 IPC theoretical processor is able to hit 2.8 in actuality.
This reflects close to maximum theoretical efficiency. When you then bump
the IPC from 3 to 5?, you claim the actual IPC only increases by .1 to 2.9.
Why, if it is so efficient for 3, is it so massively inefficient for 4 and
5? I would agree that as you add IPCs, then the relative increase in
performance would reflect diminishing returns, but I don't see why you are
claiming that 3 is close to ideal, but 4 and 5 are practically useless.

Well, first of all, I said the real-world IPCs were
given just as an example. They weren't given as actual
figures. But if we were talking about actual
real-world figures, then I'd say I was being out of my
mind generous in my examples (i.e. going from 2.8 to
2.9). Most recent figures I've seen about real-world
IPCs are that they hover around the 1.0 mark, if not
less; they're nowhere near 2.0 or 3.0. Remember, there
are still many instructions that don't complete in one
cycle, such as floating point. So going up by +0.1
real-world IPC for an increase of +1.0 theoretical IPC
is not unrealistic.

If we did have >1.0 IPCs then we should be seeing MIPS
figures that are higher than the processor's Ghz.

Yousuf Khan