[Beowulf] Re: dual core Opteron performance - re suse 9.3
Lombard, David N
david.n.lombard at intel.com
Thu Jul 14 06:59:21 PDT 2005
From: Jim Bowen on Wednesday, July 13, 2005 8:34 AM
> On Wed, 2005-07-13 at 08:37 -0400, Joe Landman wrote:
> > We find that we are talking about "per core" to our customers
> > explain that previously, there has been an implicit 1-to-1 mapping
> > between processor cores and chips, so that you could talk about
> > one and mean the other. Now however, we are talking about per core,
> > things like licensing (lmgrd) aren't going to count chips or
> > but will count cores.
> Unfortunately it isn't going to be that straightforward ... some
> are going to go by sockets/chips (Microsoft, Red Hat) and others by
> cores (your example of lmgrd and I believe Oracle). Confusion will
> abound. Oh well.
I suspect the MS & RH and Macrovision(FLEXlm) & Oracle were actually
talking about different things related to *what* their licensing is
I haven't seen a lot of confusion about socket (or chip) as it refers to
a physical thing; similarly, core also appears reasonably well
The term "CPU" appears to be the problem...
My comments represent my opinions, not those of Intel Corporation.
More information about the Beowulf