Path: utzoo!utgpu!jarvis.csri.toronto.edu!mailrus!tut.cis.ohio-state.edu!gem.mps.ohio-state.edu!usc!orion.oac.uci.edu!uci-ics!rfg
From: rfg@ics.uci.edu (Ron Guilmette)
Newsgroups: comp.sys.m88k
Subject: SERIALIZATION bit (was Re: WELCOME to comp.sys.m88k)
Keywords: 88000
Message-ID: <1989Nov12.173826.19296@paris.ics.uci.edu>
Date: 13 Nov 89 01:38:26 GMT
References: <223@m1.UUCP>
Reply-To: Ron Guilmette <rfg@ics.uci.edu>
Organization: University of California, Irvine - Dept of ICS
Lines: 27

In article <223@m1.UUCP> dave@m1.UUCP (Dave Cline) writes:
>
>WELCOME: to comp.sys.m88k
>
>
>Here are some proposed topics (partial list) to be covered by this group:
>
>	g) Future forthcoming standards activities (e.g. 88k ABI for V.4, etc.)

Ok.  I'll bite.  Is there (or will there be) an ABI for SysV.4?

>2) Discussions of the 88k architecture
>	a) Programming tricks

OK.  Here is a harder one.  I noticed in the 88100 hardware manual that
there is a control bit (in one of the control registers) that is said to
be the "SERIALIZATION" bit.  The manual (cryptically) sez that setting
this bit "serializes" the processor.  This terse note then sez to "see
section so-and-so for further information".

Well, I looked in section "so-and-so" (sorry, I don't have the book right
here just now) and guess what!  There is *no mention* of the serialization
bit in there!  What gives?

What I *really* want to know (besides *all* of the details) is whether
or not this bit could be useful to debuggers (i.e. does it disable the
otherwise confusing effects of pipelining).