[rescue] Perverse Question

[Dave McGuire]

On Sunday, June 15, 2003, at 05:55 PM, Frank Van Damme wrote:
>>    Again, don't worry.  This is a law of physics...money can't make it
>> go away.  The whole semiconductor industry acknowledges this.
>> Seriously...don't worry.
>
> I cannot but affirm watching the size of my cpu cooler grow. Every now 
> and
> then motherboard of modern pc's will tear because of the weight of the 
> cooler
> (which costs as much as the cpu) :-)

   Are you serious?  Motherboards are actually breaking due to the 
weight of the heatsinks?  I didn't know that.  That's frightening.

   I've seen HP9000 (PA-RISC) heat sinks that were a two-hand lift.  
THEY didn't break their boards.  Maybe the PC industry needs to learn 
something about systems design.

   Hmm, maybe that's what I've been saying all along! ;)

> Isn't it actually just a problem of mass? The bigger the chip the more 
> power
> it draws... make it smaller, make it cooler... or am I talking out of 
> my neck
> again? :)

   That's the biggest problem.  To get more density, you need smaller 
wires, and the wires are now so small they can barely carry the 
[miniscule] current.  Further, it's very difficult to get the heat out 
of the chip as fast as it's being produced.  They keep lowering core 
voltages, but there needs to be *some* discernible difference (meaning 
wide enough to get past the noise) so that's nearing the end of the 
rope as well.

   The poor (and *ancient*...people say VAX is old?  It's newer than 
x86!) architecture has backed them into a very dark corner in which the 
only performance gains can be had by increasing the clock rate...which 
is nearing the end of its rope.

   Thermal migration of materials (diffusion) within the chip is also an 
issue, but PC hardware isn't [generally] designed for longevity so 
that's not really a big deal.

           -Dave

--
Dave McGuire             "I've grown hair again, just
St. Petersburg, FL           for the occasion."       -Doc Shipley