Path: utzoo!attcan!uunet!dg!lewine
From: lewine@dg.dg.com (Don Lewine)
Newsgroups: comp.arch
Subject: Re: High-Priority Instructions
Message-ID: <666@dg.dg.com>
Date: 26 Jul 90 13:39:21 GMT
References: <58428@bbn.BBN.COM>
Reply-To: uunet!dg!lewine (Don Lewine)
Organization: Data General, Westboro, MA.
Lines: 19

In article <58428@bbn.BBN.COM> schooler@oak.bbn.com (Richard Schooler) writes:
>
>  The Motorola 88100's register file has only a single write port.
	{Stuff deleted}
>  I thus propose that instructions have a "high-priority" bit, which the
>compiler would place on critical-path instructions that would otherwise
>get delayed.  

There is nothing in the 88000 generic architecture that requires a single
write port.  Future 88000 family members may have multiple write ports.
Since the bit would require new silicon and a large amount of the opcode
space (the bit basicly doubles the number of opcodes) I would vote for 
additional write ports instead.

For the cases I have investigated the additional write ports are less logic
than your bit would be.

DISCLAIMER: This is my opinion as a computer architect.  It is not an
		announcement of anything by either Data General or Motorola!