home *** CD-ROM | disk | FTP | other *** search
- Xref: sparky comp.benchmarks:1766 comp.arch:11034
- Path: sparky!uunet!olivea!spool.mu.edu!agate!linus!linus.mitre.org!mbunix.mitre.org!bds
- From: bds@mbunix.mitre.org (Smith)
- Newsgroups: comp.benchmarks,comp.arch
- Subject: Re: Who wants faster machines?
- Message-ID: <1992Nov23.190312.17006@linus.mitre.org>
- Date: 23 Nov 92 19:03:12 GMT
- References: <1992Nov18.012919.2493@cs.uow.edu.au> <1992Nov18.162956.2990@ncar.ucar.edu> <1992Nov19.220352.15000@nas.nasa.gov>
- Sender: news@linus.mitre.org (News Service)
- Organization: The MITRE Corporation, Bedford, MA
- Lines: 37
- Nntp-Posting-Host: mbunix.mitre.org
-
- In article <1992Nov19.220352.15000@nas.nasa.gov> eugene@wilbur.nas.nasa.gov (Eugene N. Miya) writes:
- >>In article <1992Nov18.012919.2493@cs.uow.edu.au> pdg@cs.uow.edu.au
- >(Peter Gray) writes:
- >>>"who cares?". At our site we have ~100 SUN's.
- >>>No HP, no DEC, no RS6000. How many of our SUN users want
- >>>a faster machine? About 2. For the rest 10 Mips (SS1 type speed)
- >>>is plenty.... How many banks need 100 Mips on peoples desktops?
- >
- >This is a joke right?
- >You don't happen to be relatives of the engineers who told John Watson
- >that there wasn't a market for computers?
- >Should we stop all work on "Grand Challenge problems?"
- >I know John McCarthy posted that it is foolish to do research on turbulence.
-
-
- Sometimes people simply miss the point. Perhaps it's a cultural
- thing, I don't know. I've been involved with groups who were never
- happy with the performance of their computers, regardless whether or
- not their machines got the job done. I've also been involved with
- groups who saw computers as simply tools to solve a problem. In an
- application like word processing, where the machine sits quietly in a
- wait state most of the time, there is little reason for a 150 MIP
- chip. I know of a system where a 6 MIP box is clearly underutilized,
- yet there is a proposal to replace it with an Alpha box.
-
- At the other end of the spectrum are those problems that would take
- supercomputers years to solve, and here the need for more performance
- is paramount. But in the grand scheme of things, these problems are
- fairly rare.
-
- IBM-PCs and Macs are great machines, not because they can outrun a
- Cray (or an Alpha, or a PA-RISC) but because they provide the solution
- to a need. We've all heard the story of how Apple used a Cray to
- design the Mac, while Cray used a Mac to design their machines.
-
-
- Barry Smith
-