Path: utzoo!utgpu!jarvis.csri.toronto.edu!mailrus!tut.cis.ohio-state.edu!cs.utexas.edu!uunet!sco!seanf
From: seanf@sco.COM (Sean Fagan)
Newsgroups: comp.arch
Subject: Re: Questions on SparcStation 1 performance
Summary: somebody mention cyber!
Message-ID: <2727@scolex.sco.COM>
Date: 16 May 89 18:27:44 GMT
References: <6008@brunix.UUCP> <13024@haddock.ima.isc.com> <172@dg.dg.com>
Reply-To: seanf@scolex.UUCP (Sean Fagan)
Organization: The Santa Cruz Operation, Inc.
Lines: 21

In article <172@dg.dg.com> rec@dg.UUCP (Robert Cousins) writes:
>There are numerous examples of "hot" processors which have little or no
>support for integer divide.  If memory serves me correctly, the CDC 6xxx,
>7xxx and 17x did not have integer divide instructions.  

They also only supported integer multiply in a funky way:  if the exponent
field was 0, it did an integer 48-bit multiply.  Used the same unit as the
fp mult, of course.

>Even today, high performance processors such as the 88000 use the floating
>point units for integer division operations.

Well, actually, the 88000 (and the i860, and the Cray's) don't have divide.
They have reciporcate (actually, I belive they call it reciporocal
approximation, and, at least on the i860, you have to go through a couple of
iterations to get the "perfect" result).

-- 
Sean Eric Fagan  |    "With friends like these, who need hallucinations?"
seanf@sco.UUCP   |             -- Buddy, "Night Court"
(408) 458-1422   | Any opinions expressed are my own, not my employers'.