Re: AMD Magny-Cours
On Oct 21, 2010, at 21:54 , Steven Timm wrote: When Fermilab did our HW evaluation earlier this year we had Magny-Cours based machines, 12 core processors, available. It did work but I don't know what if any tunes were done. OK, I've found the culprit: we use only very little memory, so 16 GB/Node (4 GB/Socket) is quite sufficient. These are actually two DIMMs, using only half of the available channels. This is not a problem in itself, but since the 12-core CPUs are actually pairs of 6-core nodes, one has to make sure that the memory is properly distributed: once we've populated Slots 1A and 3A (rather than 1A and 2A), performance was back to normal. That said, there may be a slight difference (3% or so) between SL 5.4 and 5.5, but this would require some more careful checking. A. -- Ansgar Esztermann DV-Systemadministration Max-Planck-Institut für biophysikalische Chemie, Abteilung 105
AMD Magny-Cours
Hi everyone, can someone tell me what the support status of Magny-Cours is? In upstream's release notes and knowledgebase, I have found some obscure (to me) notes stating that there is some support with 5.4, 2.6.18-164.9, some more with 5.5, and still more with 6. Currently, we have a bunch of 6168-based 4-core machines here, and while they are quite stable with 5.4 and kernel 2.6.18-164.11.1, performance of our main hpc application is abysmal. It is 48-way multithreaded and yields hardly even half the expected performance; what is more, performance is varying from run to run by something like +/- 30%. Thanks, A. -- Ansgar Esztermann DV-Systemadministration Max-Planck-Institut für biophysikalische Chemie, Abteilung 105
Re: AMD Magny-Cours
When Fermilab did our HW evaluation earlier this year we had Magny-Cours based machines, 12 core processors, available. It did work but I don't know what if any tunes were done. Steve On Thu, 21 Oct 2010, Esztermann, Ansgar wrote: Hi everyone, can someone tell me what the support status of Magny-Cours is? In upstream's release notes and knowledgebase, I have found some obscure (to me) notes stating that there is some support with 5.4, 2.6.18-164.9, some more with 5.5, and still more with 6. Currently, we have a bunch of 6168-based 4-core machines here, and while they are quite stable with 5.4 and kernel 2.6.18-164.11.1, performance of our main hpc application is abysmal. It is 48-way multithreaded and yields hardly even half the expected performance; what is more, performance is varying from run to run by something like +/- 30%. Thanks, A. -- -- Steven C. Timm, Ph.D (630) 840-8525 t...@fnal.gov http://home.fnal.gov/~timm/ Fermilab Computing Division, Scientific Computing Facilities, Grid Facilities Department, FermiGrid Services Group, Assistant Group Leader.