Re: [IO-500] Naming conventions

Dear Ilene, thanks for the feedback. While entering data for these supercomputers, I found the problem is complex. There might be storage systems that are shared between some supercomputers but not all supercomputers on the site. At the moment the aggregation on this list works as follows: * Actually sites are ranked, not supercomputers or storage systems * By default a metrics is aggregated across the site, i.e., multiple storage systems add their performance, capacity, .... It is also possible to pick the min, max, or mean. (have a look at the pickers below the list), that way one could ask the question what is the best performant storage system? Maybe measuring a single site-wide file system could be possible by utilizing two supercomputers at the same time... In particular, people do this with their data archive that may remain with little change over several generations of supercomputers. The text of the HPSL should allow people to at least document the topology on the site page and to document the execution of the benchmark on the storage page, e.g., saying the best value was achieved using Supercomputer X or Y. I believe still having the supercomputers on the list is mandatory as we understand how the storage resource is used. Maybe there are sites that have 4 supercomputers on a single shared file system or two. What counts is the cluster characteristics memory throughput, bisection bandwidth, connection to storage and so on. Hopefully, they build overall a balanced cluster with storage. I can imagine, to slightly change the storage systems allowing to define which supercomputers they actually serve. Not sure if this really will resolve the problem. Resolving this would be nice though, Julian 2017-04-06 19:59 GMT+02:00 Carpenter, Ilene <Ilene.Carpenter(a)nrel.gov&gt;: -- http://wr.informatik.uni-hamburg.de/people/julian_kunkel