Since the P54C DP and especially since the P6 glueless quad MP,
Intel has been making it easier to build a processor consistent MP
system than to build a weakly ordered system.
Indeed, as I indicated, I don't think that you *can* build a weakly
ordered P6 system using standard instructions - to build a weakly
ordered P6 system you have to do something like use acceses
to an uncached page as a convention.
But, a system integrator can still build a weakly ordered
system if they want to. There may even be good reasons.
----- Original Message -----
From: Jamie Lokier <lk@tantalophile.demon.co.uk>
To: Oliver Xymoron <oxymoron@waste.org>
Cc: Linus Torvalds <torvalds@transmeta.com>; Andy Glew <glew@cs.wisc.edu>; linux-kernel <linux-kernel@vger.rutgers.edu>
Sent: Tuesday, April 25, 2000 2:30 PM
Subject: Re: Linux spin_unlock debate (fwd)
> Oliver Xymoron wrote:
> > Not only have I now gotten positive test results for PPro steppings back
> > to 1, I have confirmation from Intel folks. Thanks, Andy.
>
> Andy Glew wrote:
> > So: if you are willing to write code that should work correctly
> > on every x86 multiprocessor to date (except for some of the
> > earliest i386 and i486 MPs that were weakly ordered) you
> > can use MOVB to release the lock.
>
> I heard that Linux has been ported to i486 MPs :-)
>
> enjoy,
> -- Jamie
>
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/