Subject: Re: NetBSD on RS/6000 computers
To: Johan A. van Zanten <johan@ewranglers.com>
From: Greg Lehey <grog@au1.ibm.com>
List: netbsd-help
Date: 03/07/2002 11:41:42
*sigh*  It's difficult to know where to start.  This message seems
about as good as any.

On Tuesday,  5 March 2002 at 16:07:16 -0500, Johan A. van Zanten wrote:
>
> ---In message <20020305081834.F26327@dr-evil.shagadelic.org>
>
> On Tue, Mar 05, 2002 at 05:00:28AM -0800, Andy R wrote:
>>
>>> The current RS/6000s are PCI bus, and haven't been MCA
>>> for quite a while now.
>>>
>>> They have a Motorola PowerPC processor, nothing like
>>> the old M68k.

Well, PowerPC.  It's possible that some were supplied by Motorola, but
IBM builds its own processors.

> Jason R Thorpe wrote:
>
>> You're both wrong :-)
>>
>> RS/6000s have:
>>
>>	POWER
>>  -- or --
>>	POWER2
>>  -- or --
>>	PowerPC
>>
>> processors, depending on model.

POWER 2 is a PowerPC implementation.  This misunderstanding happens
again and again, so it's worth discussing the background.

POWER ("Performance Optimization With Enhanced RISC") was a multi-chip
architecture introduced in 1990.  In 1991, IBM formed a joint venture
with Apple and Motorola to create a follow-on architecture, PowerPC
(PC stands for "Performance Computing").  The first PowerPC model was
the 601.  Since then, all IBM POWER processors have been PowerPC, but
IBM still uses terms like POWER 2 and POWER 3 to describe them.

This should also make it clear that the term "RS/6000" is not very
specific.  There have been dozens of models with different processors,
different buses and just about everything else different.  The term
RS/6000 has fallen into disuse; modern versions are called pSeries.

>  The RISC "POWER" cpu line did precede the use of the PowerPC in RS/6000s.
> The decision to switch to PowerPC may have been political, or maybe cost
> -- perhaps IBM didn't want to spend money on two high-end RISC chip
> development lines.

It wasn't really two development lines.  PowerPC is simply a new name
for newer models of the architecture, specifically the single-chip
sets.  From the preface to "The PowerPC Architecture"

  In early 1991 it became evident that this single-chip design could
  potentially become a high volume standard in the industry.
  Accomplishing this objective would clearly require the development
  of a superior family of single-chop microprocessors, and the ability
  to supply these at competitive prices.  ... This led to discussions
  among Apple, IBM and Motorola, in which it became clear that we did
  share common objectives for the microprocessors.

> My recollection is that in 1996-1998, IBM was having trouble getting
> the PowerPC 60x to work well in Multiprocessor configs.

I think this is normal enough.  All manufacturers have had such
difficulties.

> Machines that would support more than 4 CPUs were a long time in
> coming, and i don't recall every seeing a PowerPC-based machine with
> more than 8-CPUs.

Current models have up to 32 CPUs.

>  The confirmation of this seemed to be when IBM switched "back" to the
> POWER3 line around 1998-9.

No, POWER3 is a 64 bit PowerPC.

>  If i remember correctly, the POWER line (or some evolution of it)
> was in use by the AS/400 machines throughout this period.  (Which
> still enjoy a niche market.)

Yes, the AS/400 (now known as the iSeries) also uses PowerPC.

>  One of the difficulties with the RS/6000 is its lack of a
> non-proprietary PROM.  There's some brains in there but, it doesn't
> activate the console for long after you would see on a Sun.  Until
> the AIX kernel loads, your pretty much stuck with a 3-digit red LED
> as your window into what the hell the machine is doing. (Which means
> you have to look up the codes if the boot hangs, etc.) And it makes
> it a major pain in the ass to boot off of a specific disk or type of
> media.

This is version dependent.  Modern machines use Open Firmware.

Greg
--
See complete headers for address and phone numbers