[rescue] Perverse Question

[Carl R. Friend]

   Dave McGuire writes:

> 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 know for a fact that some of the machines under my charge
at work run frighteningly hot (better than a 40 degree rise from
air intake to exhaust) and I'm sure won't have terribly long
lives.  This does not make me happy.

>   [Making a chip smaller is] 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.

   Hence copper rather aluminium traces.

> 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.

   From waht I'm given to understand, one hell of a lot of the power
is consumed (and, correspondingly, heat produced)  just by the clock
circuitry.  These boys could learn something from the async-logic
"of old".

>    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.

   Of course now they're resorting to tricks to get the clock speed up
for marketing reasons rather than technical ones.

   I don't regard the genesis of the x86 line to lie with the 8080 and
its progeny.  When was the first 8086 made?  I think it's more
contemporaneous to the VAX than older.  The original VAX, the 11/780
debuted in 1977.

>    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.

   Give it five years running at a core temperature that must approach
the boilling point of water (if not exceed it)....

+------------------------------------------------+---------------------+
| Carl Richard Friend (UNIX Sysadmin)            | West Boylston       |
| Minicomputer Collector / Enthusiast            | Massachusetts, USA  |
| mailto:crfriend at rcn.com                        +---------------------+
| http://users.rcn.com/crfriend/museum           | ICBM: 42:22N 71:47W |
+------------------------------------------------+---------------------+