>> See, this is one of the oddities of sparc64 that makes me want to put
>> SpamAssassin back on it - with 2MB cache, 333mhz CPU, it would eat 
>> through
>> messages about half as fast as a 256KB cache 2.167ghz CPU (athlon xp) 
>> -
>> shouldn't the performance margin be a LOT bigger there?
>
>   Well, it should be if we were comparing apples with apples, but 
> we're not.  There's nothing particularly speedy about the x86 
> architecture.  The only reason those guys get any performance at all 
> out of their systems is the amazing process technology which results 
> in huge clock rates.  It's still a mid-1970s processor architecture.

well, consider that the x86 processor is running at 6.5x the clock 
speed, it has:
1.  an eighth the L2 cache,
2.  a memory subsystem that probably only delivers half the memory 
bandwidth, at probably twice the latency? (I haven't looked at the 
numbers here, I'm just guessing)
3.  a processor with a 20-stage pipeline and probably about 47 cycles 
to recover from a branch-prediction miss?

-- 
George

Microsoft is a cross between The Borg and the Ferengi. Unfortunately 
they use Borg to do their marketing and Ferengi to do their 
programming.  --Simon Slavin, ASR