Path: utzoo!attcan!uunet!wuarchive!cs.utexas.edu!helps!bigtex!james
From: james@bigtex.cactus.org (James Van Artsdalen)
Newsgroups: comp.sys.ibm.pc.hardware
Subject: Re: 386SX and EMS 4.0
Message-ID: <48848@bigtex.cactus.org>
Date: 21 Oct 90 18:55:33 GMT
References: <16508@shlump.nac.dec.com> <1990Oct20.204053.20116@msuinfo.cl.msu.edu>
Reply-To: james@bigtex.cactus.org (James Van Artsdalen)
Distribution: na
Organization: Institute of Applied Cosmology, Austin TX
Lines: 24

In <1990Oct20.204053.20116@msuinfo.cl.msu.edu>, draper@cpsin2.cps.msu.edu
	(Patrick J Draper) wrote:

> I thought that all access to EMS was through the protected mode, and
> that even if you had a C&T chipset it didn't change things.

Not true.  EMS has nothing to do with protected mode.  QEMM & 386^max
kludge EMS support by using the pager in the 386.

> Also I believe that the software emulation of EMS on a 386 machine is
> faster than using the C&T chipset because the 386 can switch between
> real and protected mode very quickly compared to a 286.

But that's not the whole story.  When in virtual 86 mode, the 386 runs
slower than in real mode (not all operations).  So even if QEMM were
somewhat faster than the C&T code, the system overall is slower.

In addition, QEMM and such things have serious compatibility problems.
You're always better off with hardware support if you have it because
(1) it's net faster and (2) it's more compatible and less like to
cause the floppy drive to fail or something.
-- 
James R. Van Artsdalen          james@bigtex.cactus.org   "Live Free or Die"
Dell Computer Co    9505 Arboretum Blvd Austin TX 78759         512-338-8789