Ian,
http://lcg.web.cern.ch/LCG/C-RRB/MoU/WLCGMoU.pdf
Shows current pledges. I'm not convinced that the TDRs fully reflect the experiment resource
requests any longer. I know quite a bit of work has gone into the computing models over the last
6 months or so and these have implications for resource estimates.
Regards
Andrew
> -----Original Message-----
> From: Testbed Support for GridPP member institutes
> [mailto:[log in to unmask]]On Behalf Of Ian Stokes-Rees
> Sent: 12 August 2006 17:03
> To: [log in to unmask]
> Subject: 140 M SPECInt2K for LCG?
>
>
> Hi,
>
> I've just been going over the Alice, Atlas, CMS, and LHCb Computing
> TDRs. They seem to suggest that in 2008 the combined computing power
> they'll require is 140 million SPECInt2000 CPU years. Given that a 3
> GHz Xeon has a SPECInt2000 of about 1000, that makes (the
> equivalent of)
> 140,000 CPUs which are required. Have I mis-read (or mis-calculated)
> something? If so, what is the expected aggregated computing
> requirement
> for 2008, and if not, what is the best source of information
> describing
> how this is going to be achieved?
>
> Cheers,
>
> Ian
>
> --
> Ian Stokes-Rees [log in to unmask]
> Particle Physics, Oxford http://grid.physics.ox.ac.uk/~stokes
>
|