On Wed, May 10, 2006 at 08:39:32AM -0700, John H. Robinson, IV wrote: > On Tue, May 09, 2006 at 11:50:26PM -0700, [EMAIL PROTECTED] wrote: > > > > Yes but don't forget that your 30% performance hit just got erased > > 6 months later when you bought a CPU that is twice as fast! Moore's > > Law takes care of that 30%. You could say the same thing about > > high level langs, GUIs, JVMs, etc. > > That is not what Moore's law states. > > http://www.intel.com/technology/silicon/mooreslaw/ > > In 1965, Intel co-founder Gordon Moore saw the future. His prediction, > popularly known as Moore's Law, states that the number of transistors > on a chip doubles about every two years. > > Note this has nothing to do with density, nor with speed. > > > > 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. > >
My problem with Moore's law or the other things that pass for Moore's law is that it is intrinsically wasteful. Yes, it's great that every year there is more speed, cheaper memory and disk capacity. Yeaa. But should it be our aspiration to write such bloated and sloppy applications that we need this horsepower just to keep the same apparent performance? One of the reasons I love (not just like, LOVE) Linux is because it runs like a banshee on "old" HW that M$ has consigned to a landfill. This to me is Great Virtue. Relying on Moore's law to keep things running is Sloth and Vice. -- Lan Barnes [EMAIL PROTECTED] Linux Guy, SCM Specialist 858-354-0616 Tcl/Tk Enthusiast -- [email protected] http://www.kernel-panic.org/cgi-bin/mailman/listinfo/kplug-list
