We've been looking into workstation configurations forsolving CosmosWorks studies as quickly as possible. For the mostpart it seems that clock speed is king, especially when using thedirect sparse solver. However, I've got a fairly specific questionthat I'd appreciate someone with access to a quad core machinehaving a go at.
We're seeing 75-80% CPU usage while converging on a solution withthe iterative solver on a dual core machine, and that leaves uswondering whether more cores would appreciably reduce solution timefor that phase of the solve. If someone with a quad core machinecould do a back-to-back solve with 4 cores and 2 cores (set cpuaffinity for star.exe in task manager) noting solution time andapproximate CPU usage for each, that'd be really interestinginformation. If you're keen, a 3 core solve would complete the setnicely, too.. and anyone with dual quad xeons is welcome to step upto the plate.
For a trial problem, I'd suggest some sort of contact problem with~200k nodes - say a steel plate with a hole in it, and a pin in thehole with no penetration contact conditions. That should iteratelong enough to get some decent solve time results.
Cheers,
NickSolidworksAdministration
We're seeing 75-80% CPU usage while converging on a solution withthe iterative solver on a dual core machine, and that leaves uswondering whether more cores would appreciably reduce solution timefor that phase of the solve. If someone with a quad core machinecould do a back-to-back solve with 4 cores and 2 cores (set cpuaffinity for star.exe in task manager) noting solution time andapproximate CPU usage for each, that'd be really interestinginformation. If you're keen, a 3 core solve would complete the setnicely, too.. and anyone with dual quad xeons is welcome to step upto the plate.
For a trial problem, I'd suggest some sort of contact problem with~200k nodes - say a steel plate with a hole in it, and a pin in thehole with no penetration contact conditions. That should iteratelong enough to get some decent solve time results.
Cheers,
NickSolidworksAdministration
