Ken, among the several important issues here is CPU/chipset
architecture.  My infrastructure is Intel, so I can't speak to AMD. 
"Hyperthreading", introduced with the later P4's, and still in the old
i7 I use, is better than not having it, but not a lot.  Even with
multicore CPU's there'd be an issue of CPU scheduling at the hardware
level, dare I suggest that Intel might even be able to change that at
the microcode patch level, not to mention Linux kernel.  There is still
competition for CPU/chipset/bandwidth, that'd be different for different
architectures and there's no way to predict the user's case.

I'd go with the suggestion to note on the larger packages, those using
C++, (JAVA?), that predictions are just unreliable.  (reminding me of
some primitive peoples who count: one, two, many.)

-- 
Paul Rogers
[email protected]
Rogers' Second Law: "Everything you do communicates."
(I do not personally endorse any additions after this line. TANSTAAFL
:-)
-- 
http://lists.linuxfromscratch.org/listinfo/blfs-support
FAQ: http://www.linuxfromscratch.org/blfs/faq.html
Unsubscribe: See the above information page

Reply via email to