Relay-Version: version B 2.10 5/3/83; site utzoo.UUCP
Posting-Version: version B 2.10 5/3/83; site utzoo.UUCP
Path: utzoo!henry
From: henry@utzoo.UUCP (Henry Spencer)
Newsgroups: net.arch,net.ai,net.lang,net.lang.lisp
Subject: Re: Lisp Machines
Message-ID: <5604@utzoo.UUCP>
Date: Fri, 17-May-85 12:39:15 EDT
Article-I.D.: utzoo.5604
Posted: Fri May 17 12:39:15 1985
Date-Received: Fri, 17-May-85 12:39:15 EDT
References: <922@noscvax.UUCP>
Organization: U of Toronto Zoology
Lines: 19

In the recent AI issue of Byte, there was an article by some folks at a
company (Fairchild?) that is looking at building a super-fast AI machine.
Their analysis of supporting AI languages (notably Lisp) really well on
conventional machines ultimately boiled down to "efficient simulation of
tagged memory is the major stumbling block".  Their conclusion was that
conventional machines will be good for Lisp etc. in direct proportion to
how quickly they can (a) pick out some bits from a word and branch to one
of several places depending on the value of those bits, and (b) do an
indirect fetch which ignores some of the bits in the address register.

For example, the original 68000 is good for (b), since it ignores the top
8 bits of an address value, but its bit-extraction facilities are poor
which hurts (a).  The 68020 has better bit extraction but hits problems
on (b), since it tries to use a full 32-bit address.  And so forth.

I am not up on the intricacies of Lisp machines, but this article made sense.
-- 
				Henry Spencer @ U of Toronto Zoology
				{allegra,ihnp4,linus,decvax}!utzoo!henry