Path: utzoo!attcan!uunet!samsung!dali.cs.montana.edu!uakari.primate.wisc.edu!sdd.hp.com!zaphod.mps.ohio-state.edu!julius.cs.uiuc.edu!psuvax1!psuvm!dxb132
From: DXB132@psuvm.psu.edu
Newsgroups: comp.sys.amiga
Subject: Re: 68010
Message-ID: <90316.144548DXB132@psuvm.psu.edu>
Date: 12 Nov 90 19:45:48 GMT
References: <15556@brahms.udel.edu> <422@martin.AUSTIN.LOCKHEED.COM>
Organization: Penn State University
Lines: 21

In article <422@martin.AUSTIN.LOCKHEED.COM>, tmd@AUSTIN.LOCKHEED.COM (Tom Davis)
says:

>In article <15556@brahms.udel.edu>, jeremym@brahms.udel.edu (Jeremy
>A Moskowitz) writes:

>> Could someone pease tell me the implications of exchanging a
>> 68000 with a 68010 on the B2000 rev 4.2?

>For what it's worth, about the only thing a 68010 buys you over a 68000
>is that it has a small instruction cache that will speed up very tight
>loops. For instance, the 680x0 architecture has no native string
>handling instructions, so you have to write a tight loop to, say, copy
>the characters of one string to another. The 68010 makes these run quite
>a bit faster than on the 68000.

Actually, unrolling the loop is fastest - faster than the loop mode on the 010,
 and even faster on a regular 68000 without the loop mode.
So there's really very little need for the special loop mode...

-- Dan Babcock