Re: future computers (sorta OT)

[Jeff Fox <fox@xxxxxxxxxxxxxxxxxxx>]

Dear MISC readers:

Greg Alexander wrote:
> That is, allowing the experts to be mostly ignorant.  It's assumed that
> everything done by those who really bu[ilt the system works perfectly so
> there's no good reason to look under that level of the hood.  [snip]

> software.  Even the experts only think of system-level components, they
> don't worry about program code or even act as if they are aware of it --
> they certainly know nothing of gates or transistors.

I loved the episode where Kirk and Spock were stranded on Earth
in the 1930s.  Spock said, "I am endevoring to create a neumonic
brain circuit using stone knives and bearskins."

I think there is an anology there to what Chuck does.  He has
been working on advancing technology from the stage of stone
knives and bearskins to the level of neumonic brain circuits.
Most people don't have a clue since they are still working
with stone knives and bearskins and think the point of 
computing is to make the stone knives and bearskins invisible.

I would say that what makes StarTrek computing interesting
is that they understand the principles well enought to
build a futuristic computer out of primitive components. I
completely disagree that what is important is that they
don't need to understand what is under the hood.  Quite
the opposite.  What is under the hood must be extrememly
simple and easy to understand unlike the machines we have
today with 50 million microscopic stone knives and bearskins 
connected together in an unimaginable mess and driven by
an unimaginable mess of hundreds of megabytes of code to
do simple things.

> In some ways this does not look good for FORTH.  If the C++ fan's
> most favorite statement "It doesn't matter if it runs 10x slower,
> processors are so fast nowadays that ..." becomes true 

Not being wasteful will aways be important to anyone who cares
about performance.  Now if people don't care about performance,
cost, value, etc., if they are proud of showing off how they
can waste valuable resources so that less is avialable to
everyone, and be proud of it then they may perceive that
it isn't important. 

Some people enjoy showing off their wealth by showing that
they don't care if they throw away money on this or on that.
They have bought into the commericalism and materialism
in our society that says that people who can waste money
are better than people who can't.  

If people want to show how rich they are to their neighbors
by investing millions in worthless stocks and not caring if
they loose it, by showing that they are not afraid to bet
millions at the track and lose it, and want the most expensive 
and inefficient car or computer possible to impress the 
Jones accross the street I can understand it.  I do think
it is pretty shallow and silly, but I can certainly understand
why so many people want to say "it just doesn't matter to me
how efficient _anything_ is."  

This is not the MISC mindset however.  We say, "All computers,
regardless of cost or size have limitations.  All computers
have an efficiency factor.  You can only get the most out of
any computer by thinking about efficiency.  On the other hand
if you don't care how much it costs, if you don't care how
efficient or inefficient the computer is, you may be able
to brag that you spent more than Jones accross the street.

> then it looks like
> C++ will be the future.  

The sixties were a time of serious visible consumerism.
We were told that things would expand forever at the same
rate that they did after WWII.  We were told that people
had two cars in the garage and chicken in every pot in the
sixties and that things would continue this way into the
future.  We were told that simple projections showed that
by the time we were 50 we would all have two flying cars
in the garage and only work 5 hours a week.

The reality on the other hand was that the idea that
conspicuous consumption and the old idea that bigger was
by definition better was a dead end route.  We say that
instead of having two spaceships in the garage that
cars got much more expensive instead.  I could buy a
new Corvette for 1/10 the price back then of what it
costs now.  And back then if you earned minimum wage
you were not in a high income tax bracket.

IMHO much of the unrest of the sixties was simply that
a whole generation realized that just making the products
bigger and more expensive was not going to give us what
they promised.  The whole direction that they had told
us would work clearly wasn't going to work.  People
focused on things like improving quality of life,
considering the effect of their culture on the enviroment,
and seeing the big picture rather than buying the lie
we had been given that things could expand infinately forever.

People slowly realized that all resources are limited, fossile
fuel, raw materials, and money.  People focused on making
things more efficient so that we wouldn't just waste our
precious limited resources as had been the "fashion."  That
trend has continued up to today on pretty much everything
except computers.

With computers we still see a large group of people suggesting
that with computers efficiency isn't as issue.  For some reason
they have this absurd idea that technology is free, and
infinite.  The fact is that we have limited resources and
the only place it seems that people are still proud of being
wasteful is with their computers.  It is a fashion and status
issue.

I think even the people with their heads burried in the sand
will eventually realize that things are limited.  I think the
"future" most definiately will not be one of an infinite
expansion of inefficiency even if we hear all the time that
this "is the future."   I think even the people saying that
will eventually realize that proposing being wasteful to
demonstrate your importance to other people is not something
that will be valuable to the future of humanity.

> But that's not true either because it already
> usually doesn't matter right now if software runs 10x slower -- the
> problem is that C++ers think 10x but what really happens is 100x or
> 1000x (because they build a 10x solution on top of a 10x solution,
> yielding 100x not 20x).  

Yes, that is what I have been saying for years.  10x here, 10x there,
and 10x over here does add up, multiply actually to 1000x.  If you
ask people if they really want to pay 1000x more than needed they
may say that they enjoy showing that it isn't important to them.

>         I think this shows strengths in MISC, though.  The strength of
> MISC chips is that they can be really great, even by today's standards,
> using yesterday's fab technology.  This means we're getting at new
> ideas, not just new hacks.  RISC got at new ideas -- it gave
> performance improvements on similar processes.  The Pentium didn't
> though....it borrowed a lot of ideas, for sure, but the only great
> new thing about the Pentium is the huge engineering task involved in
> hacking these millions of features into the same chip -- something
> that wouldn't've been possible until a process small enough was
> refined.  The MercEd definitely doesn't get at new ideas -- the only
> reason it didn't exist 10 years ago is because nobody had a 30+
> million transistor fab that could mass-produce cheap chips.  If other
> chip development companies had the same level of preproduction budget
> that Intel does, they would definitely be making better products.  MISC
> qualifies as trying to understand where we're at before blindly jumping
> into the future.  Intel is making bigger and fatter MercEd before they
> stop to think and look back at the Pentium.

As long as Intel can rake in billions of dollars with the
backwards compatibility strategy they may not be too concerned
about the direction they are going.  If and when the problem
effects their profits they will need to show concern.  Until
then they can take the stance that bigger is better by def.

> I can't believe that they don't realize that
> instead of investing billions into their new fab processes that 
> they could simply investigate more thoroughly what can be done 
> with their old ones.

Well with all that dancing around in moon suits in their fab
plans making chips faster than they can sell them they don't have 
much time for thinking about totally different things. ;-)

There is an Intel plant I drive by on the road these days.  I
had to pull off one day to get a closer look.  I have never
seen anything like it.  Totally awe inspiring.  The problem I have
is that given the number and size of the buildings I didn't see
the parking lot for the million employees who must work at
that site.  Maybe they are just storing a few cubic miles of
Pentium chips in those buildings. :-)

Jeff Fox