Newsgroups: comp.parallel
From: wrankin@ee.duke.edu (William T. Rankin)
Subject: Re: SMP vs. MPP
Organization: Duke University EE Dept.; Durham, NC
Date: Fri, 6 Jan 1995 15:38:09 GMT
Message-ID: <3eeh7a$34p@news.duke.edu>

In article <3e9k5b$1487@theory.tc.cornell.edu>, shore@dinah.tc.cornell.edu (Melinda Shore) writes:

|> I think it depends on whether you're talking about the hardware
|> or the software.  From the OS level on up, the KSR certainly
|> is symmetric.  In fact, one could argue that from the hardware
|> VM level on up, the KSR is symmetric.

Good point.  I have a tendency to look at architectures as a really low level
hardware viewpoint.   Sometimes too low. :-)

The AllCache architecture is a stange beast and difficult to describe in 
classic terms.  Like, for instance, technically you *could* say that there
is no "VM" system.  I just tend to avoid associating any labels with it,
especially SMP/MPP/etc...

On another front, does anyone have a good definition, offhand, what "SMP"
is, and perhaps more importantly what it is *not*?

I figure getting a corresponding definition for "MPP" is pretty hopeless ;-)

|> --
|>         Melinda Shore - No Mountain Software - shore@tc.cornell.edu
|>                        I don't speak for Cornell.
|>           If you send me harassing email, I'll probably post it

-- 
----                                /       __/    /    /
bill rankin                        /              /    /
wrankin@ee.duke.edu               ___  /    /    /    /
philosopher/coffee-drinker       /    /    /    /    /
molecules-R-us                  /    /    /    /    /
                             _______/  __/  __/  __/

A racing start is like a dozen marketing managers with PMS, all competing
for the same on-ramp.
                                - Joe Chew



