Xref: utzoo comp.sys.ibm.pc:54279 comp.sys.ibm.pc.hardware:374
Path: utzoo!utgpu!news-server.csri.toronto.edu!clyde.concordia.ca!uunet!snorkelwacker!usc!zaphod.mps.ohio-state.edu!rpi!crdgw1!antarctica!davidsen
From: davidsen@antarctica.crd.GE.COM (william E Davidsen)
Newsgroups: comp.sys.ibm.pc,comp.sys.ibm.pc.hardware
Subject: Re: EMM manager makes 386 run slower!
Message-ID: <10181@crdgw1.crd.ge.com>
Date: 23 Jul 90 15:00:51 GMT
References: <1990Jul20.155458.12729@sun.soe.clarkson.edu>
Sender: news@crdgw1.crd.ge.com
Reply-To: davidsen@crdos1.crd.ge.com (bill davidsen)
Followup-To: comp.sys.ibm.pc
Organization: GE Corporate R&D Center, Schenectady NY
Lines: 23


In article <1990Jul20.155458.12729@sun.soe.clarkson.edu>,
bkc@image.soe.clarkson.edu (Brad Clements) writes:

|> However if I load MICEMM4G (micronics EMM emulator), or EMM386.SYS
|> (from windows 3.0), even if I don't use EMM memory for anything,
|> the system slows down to
|> 
|> 4747 Characters per second and 132 Drhystones. The whetstone
|> rating is not changed.
|> 
|> Anybody have any idea why this happens? Maybe the system hasn't
|> slowed down at all, but rather QAPLUS could be broken??

  This discussion just went on in another group. The conclusion was that
the real time to run the test didn't change, therefore EMS wasn't
slowing the system. I think some EMS systems change the clock speed, and
if a tester uses the raw clock rather than the user clocktick interrupt
the results appear slower.

  Note this is a guess, but people who timed things said the system
didn't slow. I suspect QAPLUS bypasses something and doesn't check as it
does.