Hi, The reason I responded was because I thought that the 64 bit problems that ATLAS was seeing with running its software might make for more work in maintaining the systems, and I wanted to make sure that we weren't missing something that would make dealing with the ATLAS software later on more difficult. I have a tendency to distrust new things when it comes to production systems (I only wish I had that same attitude for my personal computer purchase choices!). Cheers, Gordon. > -----Original Message----- > From: [log in to unmask] [mailto:owner- > [log in to unmask]] On Behalf Of Leonard J. Moss > Sent: Thursday, April 12, 2007 11:11 AM > To: Wei Yang > Cc: Young, Charles C.; atlas-sccs-planning-l > Subject: Re: Notes of ATLAS SCCS meeting (April 11, 2007) > > I think certifications should only depend on getting the right > results and not requiring any additional burdens on the software > developers. Within those constraints, individual Tier 2 sites > ought to have the freedom to trade off per box performance and > memory footprint against other considerations as long as they > meet their obligations to Atlas for total capacity. > > > On Thu, 12 Apr 2007 at 10:19 [-0700], Wei Yang wrote: > > > I don't know what does 'certified' mean. My original question was to > > make sure RHEL4 64bit is the right one to use. And I think we still > have > > this issue of RHEL vs SLC. I will e-mail Fred and David to get more > info. > > > > Wei Yang | [log in to unmask] | 650-926-3338(O) > > > > > > Young, Charles C. wrote: > > > I wonder what it means to certify. Results are the same? Results > are the > > > same _and_ CPU performance is no worse? Results are the same, CPU > > > performance is no worse and memory requirements are similar? Anyone > > > know? > > > > > > -- > > > Charles C. Young > > > M.S. 43, Stanford Linear Accelerator Center > > > P.O. Box 20450 > > > Stanford, CA 94309 > > > [log in to unmask] > > > voice (650) 926 2669 > > > fax (650) 926 2923 > > > CERN GSM +41 76 487 2069 > >