comp.lang.idl-pvwave archive
Messages from Usenet group comp.lang.idl-pvwave, compiled by Paulo Penteado

Home » Public Forums » archive » System 2000
Show: Today's Messages :: Show Polls :: Message Navigator
E-mail to friend 
Switch to threaded view of this topic Create a new topic Submit Reply
System 2000 [message #764] Sat, 20 February 1993 18:41
atae is currently offline  atae
Messages: 5
Registered: February 1993
Junior Member
G'Day

I am guessing that a lot of people are in the same boat with regards to
computing needs. We are planning our computing budget for H/W and S/W to
take us into the year 2000. I would very much appreciate people's input as
to the way to go. Our budget may well be in the 500-1000K pounds range.
Generally we process and analyse around 10-20 Gigabytes of spacecraft data
per year, and we expect this to increase by a factor of 100 (Cluster space
mission is the culprit) by 1996. On top of this is atmospheric and MHD
modelling, AI, Computer Vision, image processing etc.. projects competing
for resources. Everyone here programs in Fortran, and a few of us in C,
Forth, and C++. We don't want to reinvent the wheel for the upteenth time
having just moved over from Vaxen to Unix machines. My proposal has been to
go for a massively parallel system connected up to networks of PCs and
workstations. This sounds reasonable given our processing needs. I am
assuming that PCs will catch up in performance and storage to workstations,
and workstations will have to go massively parallel to compete. I have been
looking for S/W packages that we can use as our development environment,
that will be easily ported to a parallel system, and where we can easily
import our F77 and C code. This would save us a lot of development time.
So far no luck. Seems like the S/W developers are just looking 1-2 years
ahead (if that :-( Data storage has been another headache given the rapid
development of R/W optical discs. Seems like every month a better, faster,
cheaper system is released. Basically help !!!

regards
Ata <(|)>
--
| Mail Dr Ata Etemadi, Blackett Laboratory, |
| Space and Atmospheric Physics Group, |
| Imperial College of Science, Technology, and Medicine, |
| Prince Consort Road, London SW7 2BZ, ENGLAND |
| Internet/Arpanet/Earn/Bitnet atae@spva.ph.ic.ac.uk or ata@c.mssl.ucl.ac.uk |
| Span SPVA::atae or MSSLC:atae |
| UUCP/Usenet atae%spva.ph.ic@nsfnet-relay.ac.uk |
  Switch to threaded view of this topic Create a new topic Submit Reply
Previous Topic: Time-varying input
Next Topic: Request for neural network architecture code

-=] Back to Top [=-
[ Syndicate this forum (XML) ] [ RSS ] [ PDF ]

Current Time: Fri Oct 10 19:13:36 PDT 2025

Total time taken to generate the page: 0.95973 seconds