home *** CD-ROM | disk | FTP | other *** search
- Newsgroups: comp.unix.sysv386
- Path: sparky!uunet!haven.umd.edu!darwin.sura.net!rsg1.er.usgs.gov!news.cs.indiana.edu!umn.edu!kksys.com!quest!digibd!dellr4.digibd.com!rhealey
- From: rhealey@dellr4.digibd.com (Rob Healey)
- Subject: Re: Dell SVR4 (and Dell hardware)
- Organization: DigiBoard Incorporated, Eden Prairie, MN
- Date: Thu, 27 Aug 1992 18:36:54 GMT
- Message-ID: <1992Aug27.183654.17830@digibd.com>
- References: <1992Aug14.032421.22615@bluemoon.rn.com> <Bt1rp8.EKv@gator.rn.com> <1992Aug16.160841.5501@bluemoon.rn.com> <1992Aug17.115713.1131@dlpinc00.rn.com> <Bt4t2s.M1C@gator.rn.com> <1992Aug22.155636.16266@unixland.natick.ma.us> <1992Aug26.152529.4324@crd.ge.com>
- Sender: @digibd.com
- Lines: 25
-
- In article <1992Aug26.152529.4324@crd.ge.com>, davidsen@ariel.crd.GE.COM (william E Davidsen) writes:
- |> And the performance of the PC, at least under Dell V.4, is much better
- |> when there's something large running in the background. I have to run
- |> big PBM graphics jobs with nice on the Sun to keep the CPU free for
- |> other things, but the PC doesn't seem to have that problem.
- |>
- I believe this has to do with the fact that most low end RISC
- systems have problems when you try to run 2 or more programs
- that REALLY need the CPU. With SPARC I believe it has to due with
- the lesser number of registers on the cheepo SPARC implementations
- and on the others I think it's context switch time.
-
- I've found that in most cases the RISC machines run in to trouble
- ALOT faster than their CISC counter parts when you try to have
- multiple users at once or run 2 or more large CPU intensive
- programs. Mix in alot of I/O and some RISC boxes will really
- bog down.
-
- For single app situations the RISC's due very well, when you
- run multiple apps the CISC's seem to give "better" real time
- responce.
-
- Probably the nature of the RISC beast...
-
- -Rob
-