Path: utzoo!utgpu!news-server.csri.toronto.edu!cs.utexas.edu!asuvax!ncar!hsdndev!husc6!genrad!decvax.dec.com!abyss.zk3.dec.com!kenton
From: kenton@abyss.zk3.dec.com (Jeff Kenton OSG/UEG)
Newsgroups: comp.arch
Subject: Re: IEEE arithmetic
Message-ID: <1991Jun18.123732.27164@decvax.dec.com>
Date: 18 Jun 91 12:37:32 GMT
References: <3709@charon.cwi.nl> <3710@charon.cwi.nl> <1991Jun17.231640.3426@dvorak.amd.com> <3736@charon.cwi.nl>
Sender: usenet@decvax.dec.com (Usenet News System)
Reply-To: kenton@abyss.zk3.dec.com (Jeff Kenton OSG/UEG)
Organization: Digital Equipment Corporation - Nashua, NH
Lines: 17
Nntp-Posting-Host: abyss.zk3.dec.com

In article <3736@charon.cwi.nl>, dik@cwi.nl (Dik T. Winter) writes:
|>
|> The keypoint here is that the 88k and 80x87 do have *separate* control and
|> status registers.  If they are separated there would (if the unit is well
|> designen) be no need for a write to the control register to be serializing.
|> And indeed, I do not think it is on those two (at least I have found in
|> nowhere in the documentation).  I do not know about the 29050; having no
|> docs for it.
|>

The 88k does not serialize the processor when you write to the FP control
register.  You could add extra code to force serialization before a write.

-----------------------------------------------------------------------------
==	jeff kenton		Consulting at kenton@decvax.dec.com        ==
==	(617) 894-4508			(603) 881-0011			   ==
-----------------------------------------------------------------------------