Path: utzoo!utgpu!attcan!uunet!convex!mozart!loeliger
From: loeliger@mozart.uucp (Jon Loeliger)
Newsgroups: comp.arch
Subject: Re: Leading zero and pop count
Summary: Convex C1 and C2 have both
Message-ID: <705@convex.UUCP>
Date: 10 Nov 88 04:15:43 GMT
References: <10882@hall.cray.com>
Sender: news@convex.UUCP
Reply-To: loeliger@convex.com (Jon Loeliger)
Organization: Convex
Lines: 29

In article <10882@hall.cray.com> pmk@hall.cray.com (Peter Klausler) writes:
>Population count can be handy when applied to vector masks.
>After constructing an iota vector from a mask, the pop count gives you
>its length.
>
>I've never seen these useful operations in another architecture, though.
>Have you? I'd be interested in hearing about it. I'm ignorant of HW design,
>but they can't be too hard to implement.
>
>-Peter Klausler / Cray Research compiler development / Mendota Heights, MN

Yep, they are used elsewhere.  Convex C1 and C2 both have trailing-zero-count
and population counts.  There is actually an esoteric reason to prefer a
leading zero count over a trailing count....  If I'm not mistaking, there
is also now a leading-ones-place instruction microcoded into the C2 set.

Disclaimer: I'm not a hardware jock, just a compiler weenie...
jdl
------------------------------------------------------------------------------
Jon Loeliger			    loeliger@convex.com
Convex Computer Corporation	   "You should never attack an anarchist.  He
701 N Plano, Richardson, TX 75081   has nothing to lose."   Joe Bob's friend



------------------------------------------------------------------------------
Jon Loeliger			    loeliger@convex.com
Convex Computer Corporation	   "You should never attack an anarchist.  He
701 N Plano, Richardson, TX 75081   has nothing to lose."   Joe Bob's friend