This is consistent with the way APEL uses the published value to normalise the accounting reported.
-----Original Message-----
From: "Peter Gronbech" <[log in to unmask]>
To: "[log in to unmask]" <[log in to unmask]>
Sent: 31/10/08 12:33
Subject: Re: Specint
I believe the current figures we use apply to each core. That is what
Oxford and I hope all southgrid sites publish. Then by multiplying by
the number of cpu cores you have you get the value for your site.
The recommendation from hepix when measuring the spec int figures is to
run one copy of the benchmarking code on each core simultaneously and
take the figure (well the average of all of them) it produces.
The figure people actually use varies from site to site for seemingly
identical kit dependant on whether vendor figure, SPEC web site or real
measured figures are used.
I look forward to the official formula coming out from the Hepix group
on how to measure the spec in a consistent way across all sites.
Pete
--
----------------------------------------------------------------------
Peter Gronbech Senior Systems Manager and Tel No. : 01865 273389
SouthGrid Technical Co-ordinator Fax No. : 01865 273418
Department of Particle Physics,
University of Oxford,
Keble Road, Oxford OX1 3RH, UK E-mail : [log in to unmask]
----------------------------------------------------------------------
-----Original Message-----
From: Testbed Support for GridPP member institutes
[mailto:[log in to unmask]] On Behalf Of Burke, S (Stephen)
Sent: 31 October 2008 12:25
To: [log in to unmask]
Subject: Specint
Hi,
There's currently a debate going on about the meaning of the specint
value published in the information system, and I'd like to get some
feedback on what people are actually doing. The question is whether, for
multi-core CPUs, the specint rating applies to a single core or to a
whole CPU (aside from technical details about how you measure it). What
are people actually doing?
Stephen
--
Scanned by iCritical.
--
Scanned by iCritical.
|