Path: utzoo!utgpu!news-server.csri.toronto.edu!cs.utexas.edu!uunet!littlei!intelhf!ichips!ichips!glew
From: glew@pdx007.intel.com (Andy Glew)
Newsgroups: comp.arch
Subject: Re: Compilers and efficiency
Message-ID: <GLEW.91May1121028@pdx007.intel.com>
Date: 1 May 91 11:10:28 GMT
References: <4082@batman.moravian.EDU> <1991Apr28.154603.8003@rice.edu>
	<11489@mentor.cc.purdue.edu> <1991Apr29.160541.12800@tera.com>
Sender: news@ichips.intel.com (News Account)
Organization: Intel Corp., Hillsboro, Oregon
Lines: 29
In-Reply-To: bob@tera.com's message of 29 Apr 91 16:05:41 GMT

Just thought that I would juxtapose two posts to this newsgroup:

    Strange as it may seem, the dividers in today's computers can compute
    the correct quotient without having the correct remainder around to
    return to the user.  Fortunately, some can compute the correct remainder
    in one operation with a fused multiply add.

    Bob Alverson, Tera Computer
    Resident arithmetic lunatic


And:

    From the Program for the IEEE Symposium on Computer Arithmetic:

    8.1 ``Integer Division Using Reciprocals''
	Robert Alverson, Tera Computer Company

Nuff said?

(NB. I'm on Bob Alverson's side.  This sort of thing is good.)
--

Andy Glew, glew@ichips.intel.com
Intel Corp., M/S JF1-19, 5200 NE Elam Young Parkway, 
Hillsboro, Oregon 97124-6497

This is a private posting; it does not indicate opinions or positions
of Intel Corp.