Xref: utzoo comp.sys.intel:1453 comp.arch:18955
Path: utzoo!attcan!uunet!nih-csl!lhc!ncifcrf!haven!udel!wuarchive!zaphod.mps.ohio-state.edu!uakari.primate.wisc.edu!crdgw1!crdos1!davidsen
From: davidsen@crdos1.crd.ge.COM (Wm E Davidsen Jr)
Newsgroups: comp.sys.intel,comp.arch
Subject: Re: 286/386 clock frequencies, highest ? + other stuff
Message-ID: <2832@crdos1.crd.ge.COM>
Date: 2 Nov 90 14:11:38 GMT
References: <1990Nov1.165539.1359@computing-maths.cardiff.ac.uk>
Reply-To: davidsen@crdos1.crd.ge.com (bill davidsen)
Followup-To: comp.sys.intel
Organization: GE Corp R&D Center, Schenectady NY
Lines: 27

In article <1990Nov1.165539.1359@computing-maths.cardiff.ac.uk> rhl@computing-maths.cardiff.ac.uk (Robert Hartill) writes:

| I've come accross an article which comes to the conclussion that a '286 is
| as fast as a '386 (with same clock frequencies).

  Would you believe both true AND false? For 16 bit instructions this is
essentially correct. Actually there are a few instructions slightly
faster on one or the other, but for MS-DOS that's about true.

  When using the 32 bit instructions, even with a 16 bit bus and SX
chip, the speed of processing the 32 bit data goes up by about a factor
of two. So the 286 is not even ballpark close.

| What are the highest clock frequencies in use for these processors ?
| I'm not interested in special cases where a some huge clock speed has
| been achieved in a test, etc.

  I believe the fastest production 286 is 20MHz, SX is 20<Hz, DX is
33MHz. Intel talked about a 40MHz 386 at one time, but I can't recall
ever seeing a product committment.

  Note that the 486 is about 2.6 times faster than the 386 for most
things, because the clock counts for almost all instructions have been
reduced.
-- 
bill davidsen	(davidsen@crdos1.crd.GE.COM -or- uunet!crdgw1!crdos1!davidsen)
      The Twin Peaks Halloween costume: stark naked in a body bag