Relay-Version: version B 2.10 5/3/83; site utzoo.UUCP
Path: utzoo!mnetor!seismo!lll-crg!rutgers!sri-spam!sri-unix!hplabs!sdcrdcf!burdvax!bpa!cbmvax!daveh
From: daveh@cbmvax.cbm.UUCP (Dave Haynie)
Newsgroups: net.micro.apple
Subject: Re: Re: Re: InCider's comments on the new //GS
Message-ID: <845@cbmvax.cbmvax.cbm.UUCP>
Date: Mon, 6-Oct-86 15:54:54 EDT
Article-I.D.: cbmvax.845
Posted: Mon Oct  6 15:54:54 1986
Date-Received: Wed, 8-Oct-86 01:04:22 EDT
References: <2093@ecsvax.UUCP>
Organization: Commodore Technology, West Chester, PA
Lines: 50

> 
>  True but all of the 65816's instructions are 8 bits long and research
> has shown that the vast majority of tasks involve 8 bit to 16 bit quantities.

Huh?  What's your point.  Instructions on the '816 are all 8 bits long,
many of the 68000 instructions are 16 bits long.  These load in the same
time.  But your 8/16 bit argument pertains to data, not instructions.
The 68000 is just as happy with 8 bit quantities as 16 bits.
 
> A 6mhz 65816 would give the 68000 a run for its money.  The 8 bit data bus
> is a limitation but the '816 load 32 bits in 4 clock cycles, about the
> same as the 68000.

(1) 6MHz 65816 doesn't exist.  (2) A 16.6 MHz 68000 kills any '816 
permutation; a 20 MHz 68020 (software compatible with the 68000) beats
VAXen at most benchmarks, and they're available TODAY.  (3) The only 
time an '816 can load 4 bytes in 4 cycles is responding to or returning
from an interrupt, not including an instruction fetch for the returns.
A normal LDA or STA will read or write two bytes in 5 cycles.  Compare
this to the 68000 move multiple instruction.

> The 68000 design team didn't include 32 mult because they found that it was
> faster in software, this is stated in "The MC68000 design Philosophy"
> printed in Byte in '83 (I think).  The Motorola boys compared their
> 32 bit software mult to the Z8000 hardware mult ...

The problem is ALUs.  The 68000 has three 16 bit ALUs which would make a
built-in 32 bit multiply inefficient.  A 68020 does it just fine.  Where's
the '816s 8 bit multiply, then?

>> ... So I wouldn't be waiting on the edge of my seat for a 32 bit version.

> Sure the 816 took awhile, WDC didn't have Mot's big bucks, but with the
> good sales of the 65C02 and the '816 they have some cash to work with
> and an accepted product.  

WDC is too far behind.  They may do well in the future 8-bit market, but
mainly since no one else is still designing 8 bitters.  But they're not
going to do well against the 16 and 32 bit machines, because there already
exist.

> Rick Fincher
> 
> Ranger@ecsvax
-- 
============================================================================
Dave Haynie    {caip,ihnp4,allegra,seismo}!cbmvax!daveh

	These opinions are my own, though if you try them out, and decide
	that you really like them, a small donation would be appreciated.