[geeks] Best Vista story I've seen

[Doug McLaren]

On Tue, Feb 20, 2007 at 07:18:07PM -0500, Charles Shannon Hendrix wrote:

| > > Can you imagine the look someone would have given you if you asked them,
| > > in 1986, if you could use their Cray to play Doom?

Not everything done on the big iron was serious :)

| Still... I remember when some friends and I requested supercomputer time
| for a college numerical computation assignment.  It was taking our Sun
| systems 3 weeks for a run.
| 
| The gopher we had to request time from looked at us as if we'd asked to
| take Air Force One for a joyride.

I was taking a class on `computational physics' at UT, perhaps 1993 or
so (give or take a few years I guess) and I wrote a program to model
star motions in a globular cluster.  It was taking weeks (months?) to
run to get good data out of a SGI R3000 box, which was the best I had
available locally to me at the time.

But the company I worked for also ported software to Crays, so I had
access to some machines actually at Cray for porting and testing.  My
code compiled and ran on the Crays with no problems, but was only
about 6x faster than on the SGI I had locally.  Which was nice, but it
wasn't *that* big.  After talking about it with my co-workers (I was
the sysadmin, not a developer of stuff like this) it should have been
much faster than that, but I just didn't know how all the tricks
needed to make stuff run fast on the Crays, and it really wasn't time
effective for me to learn.

So ultimately I turned the project in without really finding the
results I was looking for, presumably due to my understimating the
amount of cpu time needed to do so.  Fortunately, at the upper
division level in physics, even a failed experiment is often worth an
A or A- if your work was good. :)

(I guess if I still had the code, I could try it on a PC now that's
dozens of times faster than the R3000, but while I suspect I still
have a copy of the code, I wouldn't even know where to begin to look
for it ...)

-- 
Doug McLaren, dougmc at frenzied.us                      Gone crazy - back later!