Relay-Version: version B 2.10 5/3/83; site utzoo.UUCP
Path: utzoo!watmath!clyde!cbosgd!gatech!gitpyr!kludge
From: kludge@gitpyr.UUCP (Scott Dorsey)
Newsgroups: net.arch
Subject: Re: Addressing modes
Message-ID: <1441@gitpyr.UUCP>
Date: Wed, 19-Feb-86 17:41:42 EST
Article-I.D.: gitpyr.1441
Posted: Wed Feb 19 17:41:42 1986
Date-Received: Fri, 21-Feb-86 04:23:34 EST
References: <187@anwar.UUCP>
Reply-To: kludge@gitpyr.UUCP (Scott Dorsey)
Organization: Georgia College Of Universal Knowledge
Lines: 21
Keywords: conditionality, universal
Summary: How about conditional instructions


   I was speaking with David Lane, a user assistant here, about the minimum
number of addressing modes and instructions required to compute any computible
function, and we thought about conditionality.  First of all, why can't a jump
be treated as a special case of LOAD/STORE/MOVE, because most machine implement
it that way anyway (MOV 1200, PC).  Of course, that makes conditional jumps
impossible.  So, just set one (or two) bits of every instruction aside to make
it possible to conditionally execute any instruction.  Is it worth the trouble
to decode it?  It could be treated so that as the instruction is decoded, the
condition field is checked, and if the condition is not true, the instruction
is aborted (it should only take one machine cycle to check the flag, right?).
For one-cycle instructions, they would have to be executed only if the condition
was "always execute", otherwise they would have to be delayed a cycle for the
condition field to be decoded.  Is it worth it?  Does anyone care?
-------
Disclaimer: Everything I say is probably a trademark of someone.  But
            don't worry, I probably don't know what I'm talking about.

Scott Dorsey
ICS Programming Lab, Georgia Insitute of Technology, Atlanta Georgia, 30332
...!{akgua,allegra,amd,hplabs,ihnp4,seismo,ut-ngp}!gatech!gitpyr!kludge