Re: 1teraflops cell processor possible?

Robert Myers  <[EMAIL PROTECTED]> wrote:
>>[...]
>No one really knows the answer to that.  What bothers me is that
>various branches of the federal bureaucracy have made bold statements
>about the importance of large-scale computation to practically every
>area of economic growth where technology is involved.  I'm not going
>to go bother to find the quotes, because they're more or less what
>you'd expect.
>
>By comparison with the rhetoric, the projects they have funded are
>lame and unimaginative.  The DOE asked IBM to build them a computer
>that would leapfrog the Earth Simulator on Linpack, and that's exactly
>what IBM is doing.  Now the politicians and bureaucrats can go back to
>fundraising and drawing their paychecks, respectively.
>
>If Blue Gene is the best the US can muster to lead us into a new era,
>we're in deep trouble.  Blue Gene just doesn't have what it takes to
>make a meaningful impact on molecular biology.  What it will produce
>is more of what other programs like it have produced: lots of color
>plots.

I think the problem I see with your attitude on this issue is
that the truly fundamentally hard problems seem to be to some
large degree to be algorithms and software rather than hardware.

If there were a software pull, someone would push hardware
in that direction.  There is good reason to think that from
a technical perspective, developing the sorts of software to
do those problems better would be good, but it's proven rather
hard in practice, including in PhD thesies and random researchers
reaching out in freethinking directions.  Even if it had to be
hand-done to some degree, if it was doable for some of the problems
there would be money right there for doing it.

Throwing money at hardware problems to run the known algorithms
in larger parallelism works, to a predictable degree.  To make the
great leaps, we need some great leaps in concept and algorithm
which have as of yet at least largely eluded humankind as a whole.
That is not the sort of problem that you can solve with money.
It's waiting the right bright person and the right supporting
developments for them to make the right insights.

The question is; given the value of some of those problems,
is it worthwhile for society to spend money on the ugly hack
way we do it now being scaled up now, or should we just not bother
and wait for the great leap that may come?

The government wants to do some of those things now, and commercial
companies are making money off doing some of those things now,
so I am guessing that the value of those problems is worth the
incremental improvements we can make now.

Banging your head on the wall and demanding that the next
Einstein, Feynman, Hawking pop up and solve 'the problem' is
not a reasonable  strategic plan 8-)


-george william herbert
[EMAIL PROTECTED]