 |
 |
On 06/04/2011 17:40, Stephen Burke wrote: > Testbed Support for GridPP member institutes >> [mailto:[log in to unmask]] On Behalf Of Andrew McNab said: >> Yes to all of the above. I'm not arguing against >> hyperthreading - just >> saying it's not true that "hyperthreaded CPUs and cores are >> effectively the same thing". > > The question is whether they're effectively the same for the purpose > of measuring resource usage, i.e. that you calculate the HEPSPEC by > running cores*hyperthreads copies of the benchmark, and then "charge" > the jobs for using HEPSPEC*time resources (assuming that the system > is full of jobs at the time). If you think that's wrong, what do you > think it should be? The definition should be able to take account of, for example, scenarios like having more job slots than cores but less job slots than cores*hyperthreads. You can easily imagine sites limiting themselves that way for memory reasons. It matters whether job slots are occupying extra cores or just extra hyperthreads. Andrew -------------------------------------------------------------- Dr Andrew McNab, High Energy Physics, University of Manchester