Article 4627 of comp.sys.acorn:
Path: rusmv1!news.belwue.de!ira.uka.de!sol.ctr.columbia.edu!zaphod.mps.ohio-state.edu!qt.cs.utexas.edu!cs.utexas.edu!swrinde!gatech!bloom-beacon!eru!hagbard!sunic!chalmers.se!dtek.chalmers.se!d1dd
From: d1dd@dtek.chalmers.se (Daniel Deimert)
Newsgroups: comp.sys.acorn
Subject: Dhrystones/Whetstones (was Re: Arm3 question)
Message-ID: <9070@chalmers.se>
Date: 11 Feb 92 11:04:21 GMT
References: <9202060133.AA00937@ucbvax.Berkeley.EDU> <1992Feb11.095429.163817@dstos3.dsto.oz.au>
Sender: news@chalmers.se
Organization: Chalmers University of Technology, Gothenburg Sweden
Lines: 25

rws@dstos3.dsto.oz.au writes:

>with a 780 yielding 1.  If what you are saying is true then the MIPS quoted
>nowdays are fairly well useless giving virtually no basis for comparison of

There are several more or less sophisticated tests which cater for the
variation between instruction sets. One is 'Dhrystone' (integer, memory),
another is Whetstone.

Sample approximate dhrystone figures are:

	Amiga 500	 1000 (cc -O)
	Atari 1040ST	 1000 (mwc cc -O)
	Amiga 3000	 5500 (cc -O)
	Acorn A3000	 6000 (in mode 0, 4000 in mode 15)
	Sparcst. SLC	16000 (cc)
	Acorn A5000	17000
	PC 486/33 MHz	25000 (gcc -O)
	SPARCstation II	32000 (cc)

The dhrystone test fits into mosts caches, since it is quite small.

--
Daniel Deimert			Chalmers University of Technology, Sweden
d1dd@dtek.chalmers.se