home *** CD-ROM | disk | FTP | other *** search
- Newsgroups: comp.arch
- Path: sparky!uunet!mcsun!sun4nl!relay.philips.nl!prle!reyniers
- From: reyniers@prl.philips.nl (reijnierse p)
- Subject: Re: MFLOP for some old machines.
- Message-ID: <1993Jan21.114635.11148@prl.philips.nl>
- Sender: news@prl.philips.nl (USENET News System)
- Organization: Philips Research Laboratories, Eindhoven, The Netherlands
- References: <1993Jan19.180916.19186@qucis.queensu.ca> <1993Jan20.225851.1@cc.curtin.edu.au>
- Date: Thu, 21 Jan 1993 11:46:35 GMT
- Lines: 39
-
- In article <1993Jan20.225851.1@cc.curtin.edu.au> zrepachol@cc.curtin.edu.au writes:
- >In article <1993Jan19.180916.19186@qucis.queensu.ca>, wong@qucis.queensu.ca (Tak Shing Wong) writes:
- >> Hi,
- >> Please forgive me if the following question is already is
- >> any FAQ.
- >> Can someone please tell me the performance for the
- >> following machines in terms of MFLOP,
- >> 1) uVax
- >
- >About .3. Hard to stick a good number on it, as many instruction are emulated.
- >
- >> 2)Sun3/75
- >> 3)Vax 780
- >
- >1. give or take eta. If its SPEC, its is DEFINED to be 1
- >
- >> 4) Sun3/16/FPA
- >> 5)Dec 8600
- >
- >3 or so. The numbers will differ from 3x a 780, acording to which instruction
- >mix you use for the measurement.
- >
- >~Paul
- >
- If you mean Linpack MFLOPS the numbers are:
-
- uVAX II .13
- SUN 3/50 .087 (with 68881 fp processor)
- SUN 3/160 .10 " " " "
- VAX 780 FPA .11
- DEC 8600 .48
-
- Piet Reijnierse
-
- --
- Piet Reijnierse Philips Research Laboratories
- tel. +31 40 743972 Building WYp room 4
- fax +31 40 744810 Prof Holstlaan 4
- email: reyniers@prl.philips.nl 5656AA Eindhoven
-