Path: utzoo!attcan!utgpu!utstat!jarvis.csri.toronto.edu!mailrus!tut.cis.ohio-state.edu!ucbvax!hplabs!well!theobaby
From: theobaby@well.UUCP (Paul Theodoropoulos)
Newsgroups: comp.sys.amiga
Subject: Re: 68010
Message-ID: <14440@well.UUCP>
Date: 6 Nov 89 01:12:53 GMT
References: <1220@rodan.acs.syr.edu>
Reply-To: theobaby@well.UUCP (Paul Theodoropoulos)
Distribution: na
Organization: Whole Earth 'Lectronic Link, Sausalito, CA
Lines: 10

68010 runs at stock amiga speed (7.14Mc). The performance improvement is due to
a three instruction cache, specifically for itty-bitty loops. surprisingly, it
works, and provides variously 5% to 20% improvement OVERALL. Some programs will
show not a whit of improvement, due to loops longer than three instructions. But
it seems to occur often enough that it helps. Some programs will CRASH though,  so you must install a trap for the one privileged instr. (move(SR)). There are
PD progs available to do this.
  We can thank the little 68010 for the development of the 68020. the 010 
supports virtual machine states, which allowed Motorola to create the 020 in 
software before they committed to silicon. Nifty little chip!.
>>>>Destroy bandwidth wasting signatures!! Paul Theodoropoulos, theobaby@Well<<