My Community

I am running a parallel vasp job on a cray xt3. The vpu timings are significantly greater than the cpu timings:

grep LOOP OUTCAR
LOOP: VPU time 226.59: CPU time 56.65
LOOP: VPU time 246.93: CPU time 61.73
LOOP: VPU time 223.02: CPU time 55.76
LOOP: VPU time 222.72: CPU time 55.68
LOOP: VPU time 223.82: CPU time 55.95
LOOP: VPU time 223.36: CPU time 55.84
LOOP: VPU time 223.04: CPU time 55.76
LOOP: VPU time 222.86: CPU time 55.71

I also run similar parallel vasp jobs on ibm p4/p5 and sgi servers. On the ibm p4/5 and sgi servers, the vpu and cpu timings are usually nearly identical. Any ideas as to what is happening with respect to the timing differences on the cray xt3 (and is this a problem)?

Hi,

We're sorry that we didn’t answer your question. This does not live up to the quality of support that we aim to provide. The team has since expanded. If we can still help with your problem, please ask again in a new post, linking to this one, and we will answer as quickly as possible.

Best wishes,

VASP