Path: utzoo!yunexus!geac!daveb
From: daveb@geac.UUCP (David Collier-Brown)
Newsgroups: comp.arch
Subject: Re: [is] RISC a short answer??
Summary: Yes, for Honywell DPS-8 vCISC
Message-ID: <2705@geac.UUCP>
Date: 6 May 88 13:30:45 GMT
Article-I.D.: geac.2705
Posted: Fri May  6 09:30:45 1988
References: <1036@nusdhub.UUCP> <1988May3.224604.2252@utzoo.uucp> <383@m3.mfci.UUCP> <770@l.cc.purdue.edu>
Reply-To: daveb@geac.UUCP (David Collier-Brown)
Organization: The [cg. Yac Co. Ltd. Pty. Inc. Etc.
Lines: 21

In article <770@l.cc.purdue.edu> cik@l.cc.purdue.edu (Herman Rubin) writes:
>It seems that, instead, there is great merit in a VCISC design, in which
>useful instructions are included to decrease the number of instructions needed
>in a program.

  They're both tradeoffs, so there **have** to be multiple
solutions.  It happens that RISC fits the external-to-system state
better for small, adventurous companies.  I could do a vCISC and
move more functionality into hardware (assuming I didn't mispredict
what to move!!!!!) and get a competitive processor.  I just couldn't
do it without great expenditures of time and money.
  So I stick with RISC-y little things for Unixes and big Honeybuns
for GCOS-y things.

--dave (I'm not actually working for honeywell any more,
	 but you get the idea) c-b
-- 
 David Collier-Brown.                 {mnetor yunexus utgpu}!geac!daveb
 Geac Computers International Inc.,   |  Computer Science loses its
 350 Steelcase Road,Markham, Ontario, |  memory (if not its mind) 
 CANADA, L3R 1B3 (416) 475-0525 x3279 |  every 6 months.