[comp.arch] UMA NUMA

Uwe.Baumgarten@arbi.informatik.uni-oldenburg.de (Uwe Baumgarten) (06/11/91)

Hi,
where can I find the definition of the terms
  -- UMA
  -- NUMA
  -- NORMA
?
Where are they cited first ?

Thanks,   Uwe

Uwe.Baumgarten@arbi.informatik.uni-oldenburg.de
-- 
*******************************************************************************
* From: Uwe Baumgarten                      UUCP: baumgarten@uniol            *
*       Uni Oldenburg - FB Informatik       BITNET: 011580@DOLUNI1            *
*       Postfach 25 03                      Tel:  (0441) 798-4518             *
*       D - 2900 Oldenburg                                                    *
*       Germany                                                               *
*                             Uwe.Baumgarten@arbi.informatik.uni-oldenburg.de *
*******************************************************************************

bret@orac.UUCP (Bret Indrelee) (06/13/91)

In article <5799@uniol.UUCP> Uwe.Baumgarten@arbi.informatik.uni-oldenburg.de (Uwe Baumgarten) writes:
>Hi,
>where can I find the definition of the terms
>  -- UMA
>  -- NUMA
>  -- NORMA
>?
>Where are they cited first ?
>
>Thanks,   Uwe

Can't give citations, sorry.

The first two are:
UMA	Uniform Memory Architechure.
NUMA	Non-Uniform Memory Architechure.

Both terms are from parallel (sp?) processing, and refer to whether all
processors can access any memory location with the same delay (UMA) or
a system where the access time depends on the memory location (NUMA).

-Bret
-- 
------------------------------------------------------------------------------
Bret Indrelee		|	Our mail is still somewhat unreliable.  Sorry.
uunet.uu.net!cs.umn.edu!kksys!edgar!orac!bret		-And still trying

oasis@gary.watson.ibm.com (GA.Hoffman) (06/14/91)

I believe Rick Raschid is created with these terms.
CMU.Mach.

-- 
gary a hoffman
RISC Systems, Watson Research

wright@Stardent.COM (David Wright) (06/15/91)

In article <1991Jun13.173302.21432@watson.ibm.com>
oasis@gary.watson.ibm.com (GA.Hoffman) writes: 
>I believe Rick Raschid is created with these terms.
>CMU.Mach.

Well, maybe.  But I tried reciting them in various orders and
combinations and it certainly didn't create him here.

Someone else may have better luck.

  -- David Wright, not officially representing Stardent Computer Inc
     wright@stardent.com  or  uunet!stardent!wright

"He doesn't know when he's beaten, this boy.  He doesn't know when he's
winning, either.  He doesn't have any sort of sensory apparatus known
to man."  -- Monty Python

jrm@stegosaur.cis.ohio-state.edu (John R. Mudd) (06/17/91)

In article <374@orac.UUCP> bret@orac.UUCP (Bret Indrelee) writes:
>In article <5799@uniol.UUCP> Uwe.Baumgarten@arbi.informatik.uni-oldenburg.de (Uwe Baumgarten) writes:
>Can't give citations, sorry.

%A Richard Rashid
%T Designs for Parallel Architectures
%J Unix Review
%D April, 1987
%P 37-43

>The first two are:
>UMA	Uniform Memory Architechure.
>NUMA	Non-Uniform Memory Architechure.

'Architecture' should be 'access'.

NORMA   No Remote Memory Access

... John

Rick.Rashid@cs.cmu.edu (06/18/91)

>From: wright@Stardent.COM (David Wright)
>Subject: Re: UMA NUMA
>Date: 14 Jun 91 22:09:50 GMT
>
>In article <1991Jun13.173302.21432@watson.ibm.com>
>oasis@gary.watson.ibm.com (GA.Hoffman) writes:
>>I believe Rick Raschid is created with these terms.
>>CMU.Mach.
>
>Well, maybe.  But I tried reciting them in various orders and
>combinations and it certainly didn't create him here.
>
>Someone else may have better luck.
>
>  -- David Wright, not officially representing Stardent Computer Inc
>     wright@stardent.com  or  uunet!stardent!wright


Hmm.  That's funny, it worked for me.  Perhaps you
didn't do it right.

-Rick Rashid