Lpc2000

Lies, damned lies, statistics and benchmarks.  In about that order ;)

An accurate indisputable benchmark I've found generally covers too narrow 
an area to have a general use. For example pin toggling can be made a 
fairly bulletproof benchmark but really doesn't matter unless you have a 
particular need to toggle a pin quickly.  Likewise it's fairly easy to time 
a null loop but that says little about how an application will behave.  The 
benchmark is that case is accurate, indisputable and pointless (or nearly so).

A benchmark that purports to be generally useful generally is not accurate 
and indisputable.  The classic whetstone and dhrystone benchmarks have been 
the subject of endless disputes (and IIRC compiler tweaking).

Having said that they can provide some order of magnitude checking.  They 
can be useful but remember they all come with biases (some of them not 
apparent).

As a sage once said the only benchmark with any meaning is the application 
you are going to run.

Robert

" 'Freedom' has no meaning of itself.  There are always restrictions,
be they legal, genetic, or physical.  If you don't believe me, try to
chew a radio signal. "

                         Kelvin Throop, III