> if a quarter-inch barn only costs a penny, what's to stop you from blowing
> $20 and spreading a couple thousand of them around the farm? keep
> redundant copies of the harvest in all of them, and you don't have to care
> if one gets blown away.
Sorry, it does not scale.
> smaller basic technology means a lower cost of redundancy, and higher
> redundancy means higher reliability. today's chips devote a certain
> number of transistors to on-board testing hardware. three processing
> units do the same calculation in paralell and compare the answers they get.
> if two are identical and one differs, the consensus value gets passed on.
> if all three differ, the calculation has to be run again.
The pentium already has two or four CPU's, but each tries to do
different things to speed the work load. They don't check each other so
as to maintain lower power consumption.
> if individual transistors get small enough, we won't necessarily see
> smaller chips, but we're almost guaranteed to see additional redundancy in
> the same designs. if you reduce a transistor to half its present size,
> you can produce a chip which is the same size, and does the same thing, but
> has 100% redundancy on every component.
There are rather strong physics limits when it comes to the
fabrication process. Heating causes some random vibration, and the flow
of electrons does move atoms slowly. This kind of wear, or atomic drift,
eventually alters characteristics till devices fail. We've gotten a lot
better at reducing this, but can not prevent it.
> as a flight of fancy, imagine a CPU which is 100 x redundant. you could
> overclock the hell out of the thing, because each transistor only sees a 1%
> duty cycle and the die is less vulnerable to overheating. gang the
> transistors in groups of five under the voting protocols described above,
> and you have a massively reliable system in which each component only sees
> a 5% duty cycle. blow 40% of the components, and there's still a decent
> chance that every operational unit will still be working and redundant.
As sizes diminish, some is dedicated towards redundancy and testing.
However, manufacturers bent on cost control have done such things as
remove parity circuits from our memory chips, etc. I personally think that
is rather stupid... but marketing types don't care what a few intelligent
people think; they just want to make money till someone sues the hell out
of a few people for some grievous catastrophe! Then the rest try to prove
that it never happened, no one ever warned them, etc. etc.
> >> Chips are not
> >> shrinking in any significant way, and are not at all likely to
> >> become microscopic. Where would you attach the pins?
>
> another flight of fancy.. change the design of the chip and socket.
> eliminate the pins entirely and replace them with highly redundant contact
> points along the entire inside surface of a hollow package:
There are rubber mats used on LCD displays that work to connect
metalized areas. I know the guy who invented some of that, Ed Slovakian,
a brilliant fellow in a wheel chair, trapped since birth in a body with
cerebral palsy.
Other means include putting more chips in the same carrier and wiring
them together on a substrate. This is called a hybrid chip.
Some effort has been made to stack hybrid chips. The ceramic plates
do offer greater heat conductivity, but one still has the problem of
dissipating heat.
> the packages themselves don't have to get smaller, but we can get
> significantly more power out of the same sized package.
One of the major problems today, is heat dissipation. Till we move to
isotope refined diamond substrates, we will continue to have very serious
heat dissipation problems.
The best thermal conductor on the planet is diamond, some six times
that of copper. If the diamond is purified to be all the same isotope of
carbon, the heat conductivity goes up even more. (Little things I learned
doing something for a semiconductor equipment manufacturer.)
We have had some movement towards optical computing, but this is not
making a lot of waves as of yet. Because it is a totally different
technology, we have the same problem the airlines faced -- railroads were
not interested in the technology, because they thought they were in the
railroad business, not the transport business. Other people had to invest
in the technology, and eventually overturned the railroad business.
Will optical technology take over? Probably not till we have another
arms race. If we don't, it won't, not for a long time.
[EMAIL PROTECTED] ------------------ [EMAIL PROTECTED]
----------------------- IMAGINEERING --------------------------
----------------- Every mouse click, a Vote -------------------
---------- Do they vote For, or Against your pages? -----------
----- What people want: http://www.mall-net.com/se_report/ ----
---------------------------------------------------------------
--- Have you analyzed your viewer's footprints in the logs? ---
--- Webmaster's Resources: http://www.mall-net.com/webcons/ ---
--- Web Imagineering -- Architecture to Programming CGI-BIN ---
---------------------------------------------------------------
____________________________________________________________________
--------------------------------------------------------------------
Join The Web Consultants Association : Register on our web site Now
Web Consultants Web Site : http://just4u.com/webconsultants
If you lose the instructions All subscription/unsubscribing can be done
directly from our website for all our lists.
---------------------------------------------------------------------
