Relay-Version: version B 2.10 5/3/83; site utzoo.UUCP
Path: utzoo!mnetor!uunet!husc6!bbn!rochester!PT.CS.CMU.EDU!B.GP.CS.CMU.EDU!ralf
From: ralf@B.GP.CS.CMU.EDU (Ralf Brown)
Newsgroups: comp.sys.misc
Subject: Re: Weighty instructions (really Dhrystones)
Message-ID: <156@PT.CS.CMU.EDU>
Date: Mon, 12-Oct-87 21:47:38 EDT
Article-I.D.: PT.156
Posted: Mon Oct 12 21:47:38 1987
Date-Received: Wed, 14-Oct-87 03:27:29 EDT
References: <1138@water.waterloo.edu> <2452@cbmvax.UUCP> <7422@e.ms.uky.edu> <90@piring.cwi.nl> <1866@gryphon.CTS.COM>
Sender: netnews@PT.CS.CMU.EDU
Organization: Carnegie-Mellon University, CS/RI
Lines: 22

In article <1866@gryphon.CTS.COM> jdow@gryphon.CTS.COM (Joanne Dow) writes:
>Trevor Marshall tested one of his 68020/68881 plugins for the PC at 35MHz.
>That baby turned out over 7000 dhrystones. Eat hot bytes 80386!
>
>>Steven Pemberton, CWI, Amsterdam; steven@cwi.nl
>-- 
>	BIX:jdow
>	INTERNET:jdow@gryphon.CTS.COM
>	UUCP:{akgua, hplabs!hp-sdd, sdcsvax, ihnp4, nosc}!crash!gryphon!jdow

Hmm... a 16 MHz 80386 turns out ~5500 dhrystones using 32-bit instructions*,
so it will churn out ~7000 dhrystones at 20 MHz, and over 12,000 dhrystones 
at 35 MHz.  What was that about "eat hot bytes"?  And I've heard that Intel 
intends to keep upping the speed rating of 386's until they reach 32 MHz--
which should allow 40 MHz operation with selected chips.  [I wouldn't mind
having a 40 MHz 386 machine.  Norton SI of 42, anyone?]

I hope this doesn't degenerate into another MCIBTYC war....

[*] in fact, there are two entries in the March 1987 Dhrystone database for
16 MHz 386's getting ~7000 dhrystones with UNIX SVr3 and the Green Hills C 386
compiler.