Relay-Version: version B 2.10 5/3/83; site utzoo.UUCP
Path: utzoo!mnetor!uunet!husc6!cmcl2!brl-adm!umd5!eneevax!mimsy!oddjob!gargoyle!ihnp4!homxb!homxc!dwc
From: dwc@homxc.UUCP (D.CHEN)
Newsgroups: comp.arch
Subject: Re: Sort Co-Processors
Message-ID: <1759@homxc.UUCP>
Date: Fri, 16-Oct-87 14:43:27 EDT
Article-I.D.: homxc.1759
Posted: Fri Oct 16 14:43:27 1987
Date-Received: Sun, 18-Oct-87 02:21:36 EDT
References: <112@sdeggo.UUCP> <7473@ism780c.UUCP> <379@srs.UUCP>
Organization: AT&T Bell Laboratories, Holmdel
Lines: 14

In article <379@srs.UUCP>, dan@srs.UUCP (Dan Kegel) writes:
> In article <112@sdeggo.UUCP> dave@sdeggo.UUCP (David L. Smith) writes:
> > Has anyone out there ever run across a sorting co-processor?  
> > Is there any research being done in this, or does it sound like a useless
> > idea?
> 
> I heard somewhere that, using log N simple sort processors arranged cleverly,
> one could perform a sort in N-time.  Has this ever been tried in hardware?

there are O(N) sort algorithms for "pyramid" architectures.  i forget
the references.

danny chen
homxc!dwc