Path: utzoo!attcan!uunet!husc6!rutgers!netsys!lll-winken!maddog!brooks
From: brooks@maddog.llnl.gov (Eugene Brooks)
Newsgroups: comp.arch
Subject: Re: A simple question on RISC
Message-ID: <13844@lll-winken.llnl.gov>
Date: 14 Nov 88 23:42:29 GMT
References: <76083@sun.uucp> <559@dms.UUCP> <1021@raspail.UUCP> <7819@winchester.mips.COM> <1688@scolex>
Sender: usenet@lll-winken.llnl.gov
Reply-To: brooks@maddog.UUCP (Eugene Brooks)
Organization: Lawrence Livermore National Laboratory
Lines: 9

In article <1688@scolex> seanf@sco.COM (Sean Fagan) writes:
>And, of course, Cray's don't have divides at all.  Does anybody besides me
>get the impression that Seymour don't like 'em? 8-)
Seymour made the observation that floating point divides are much less
frequent than multipy or add so one could implement them with a less
complex reciprocal approximation unit followed by a Newton Raphson hit or
two.  This disproves the notion that Semour just hacked in what he could do
fast, he obviously made careful decisions about what to put in hardware
based on how heavily instructions were used and how fast they could be
implemented.