From: Stewart Stremler <[EMAIL PROTECTED]>
begin quoting John H. Robinson, IV as of Wed, May 10, 2006 at 08:39:32AM
-0700:
[snip]
> Let's assume, though, that speed did double. So while your 30%
> performance hit kernel has caught up to speed, the full speed kernel is
> still 30% faster. TIme may improve all things, but all things get
> improved. Something that lacks will still lack.
...and meanwhile, programs don't actually get faster. The more compute
resources they have, the more useless crap they try to do. :-/
I wonder how long this can remain true. Intel and AMD are basicly giving up
the MHZ wars and moving to the core wars. Individual core speed is still
increasing, but the pace of it is decreasing. I see some a performance wall
looming in the next few years- either software will have to get better (or
at least better at parallel processing) or we have to give up performance
boosts and watch as our bloatware begins to get slower.
Gabe
--
[email protected]
http://www.kernel-panic.org/cgi-bin/mailman/listinfo/kplug-list
