Relay-Version: version B 2.10 5/3/83; site utzoo.UUCP
Path: utzoo!mnetor!uunet!seismo!sundc!pitstop!sun!decwrl!labrea!rutgers!im4u!ut-sally!utah-cs!utah-gr!uplherc!esunix!bpendlet
From: bpendlet@esunix.UUCP (Bob Pendleton)
Newsgroups: comp.arch
Subject: Re: Serial Search Machines
Message-ID: <550@esunix.UUCP>
Date: Fri, 30-Oct-87 09:42:45 EST
Article-I.D.: esunix.550
Posted: Fri Oct 30 09:42:45 1987
Date-Received: Thu, 5-Nov-87 20:09:47 EST
References: <2667@uunet.UU.NET>
Organization: Evans & Sutherland, Salt Lake City, Utah
Lines: 47

in article <2667@uunet.UU.NET>, mo@uunet.UU.NET (Mike O'Dell) says:
> 
> Sequential text search machines have been around for a long
> time, but recently they have started to become affordable
> for many applications.  
	.
	.
	.
> Like everything highly specialized, they can win very big and
> lose very big.
> 
> Their biggest assest is they can scan data with little or
> no preprocessing.  
	.
	.
	.
> For other tasks like searching large resident
> collections, however, their strength can become a great 
> weakness because they must read through all the data for
> each and every search.  If the collection is say one to two
> gigabytes, which is rather modest, dumping that much data
> off the filesystem and through the box for each query quickly
> gets pretty painful.

> More traditional search systems build some kind of index
> in one pass and then "save the work" by consulting the index
> instead of the data to process queries.  

> 	-Mike O'Dell

An alternative is to build a seqeuntial text search processor on a chip,
attach one to each drive in the storage system and use an index to select
chunks of text to search. This can give you the flexibility of text search
and the speed of an indexed system. You should be able to process an
average query on a 50 gb textual database in less than a couple of seconds.

Simulating a system like this was my masters thesis topic. I'd give more
exact numbers but its been a few years since I've read the thing. Anyone
still working on the project want to fill us in on the latest and greatest
progress?

			Bob P.
-- 
Bob Pendleton @ Evans & Sutherland
UUCP Address:  {decvax,ucbvax,ihnp4,allegra}!decwrl!esunix!bpendlet
Alternate:     {ihnp4,seismo}!utah-cs!utah-gr!uplherc!esunix!bpendlet
        I am solely responsible for what I say.