"Which is an unimportant consideration to performance, thanks to register renaming."
You are making this up.
How does that work in an in-order machine? Besides, it doesn't solve the problem of having to spill registers to the stack when you run out.
"What makes one architecutre more branchy than another?"
Lots of things. In general, though, it all depends on the support for control structures.
"but I don't see how it's relevant to performance."
As I have stated, the more branches, the more opportunities for a branch miss prediction. That means a pipe flush.
"I don't know what you're thinking, CJ, but when someone sees one Netbook marketed as "Internet web browser" and another marketed as "Internet web browser as well as support for all the applications on your PC""
Other than the fact that no one is marketing netbooks as supporting your PC applications, I suppose you have a point. Now, Apple might. But they have a stronger case for actually doing it.
"I don't buy this. I've looked at the OMAP datasheets, and I haven't found any significant power or die size advantages relative to Atom"
At 65nm, the processor core for A8 occupies about 9mm^2. Are you claiming that the processor core of an Atom is smaller than that?
"Why wouldn't the average end user prefer Windows?"
Because to include and support it, the costs are pushed up to about what a regular laptop would cost. One that doesn't have a dinky screen. And while it might be able to run those applications, it wouldn't run them very well. |
