Newsgroups: comp.sys.ibm.pc.hardware
Path: utzoo!utgpu!news-server.csri.toronto.edu!rpi!think.com!zaphod.mps.ohio-state.edu!wuarchive!uunet!world!iecc!johnl
From: johnl@iecc.cambridge.ma.us (John R. Levine)
Subject: Re: 486SX - Intel now telling lies
Message-ID: <1991May23.143329.20564@iecc.cambridge.ma.us>
Organization: I.E.C.C.
References: <1991May14.200856.1431@ux1.cso.uiuc.edu> <1991May15.210339.17118@unlv.edu> <1561@aoa.UUCP>
Distribution: usa
Date: Thu, 23 May 91 14:33:29 GMT

>In article <1991May15.210339.17118@unlv.edu> whitney@jimi.cs.unlv.edu (Lee Whitney) writes:
>[trade article:]
> ....  In addition, the 20Mhz 486sx chip delivers a 40 percent greater
>performance than the 33Mhz 386 processor.

This could be true.  A 486 does between 2 and 3 times as much work per
cycle as a 386, so a 20MHz 486 is analogous to a 40-50MHz 386.  In real
systems, of course, memory system delays and I/O will have a big effect.
I recently swapped a 25 MHz 386 motherboard for a 25 MHz 486.  It's a lot
faster, but it's no factor of three, since I still have the same old
screen and disk controllers.

-- 
John R. Levine, IECC, POB 349, Cambridge MA 02238, +1 617 492 3869
johnl@iecc.cambridge.ma.us, {ima|spdcc|world}!iecc!johnl
Cheap oil is an oxymoron.

