[MITgcm-support] question about TIMER stats breakdown

[Daniel Goldberg]

Hi All

Apologies if this is made clear in the documentation.

I am wondering about the system time/user time breakdown of the TIMER
stats. Might it vary from machine to machine what is considered "system
time" or is it pretty standard? My understanding is that system time refers
to time spent in kernel code rather than user code, but I'm wondering if
that's generalized e.g. to external libraries, such as PETSc, or if my long
system times are due to slow MPI exchanges (in the particular S/R I am
looking at there are no file reads or writes, save writing to STDOUT).

Thanks very much
Dan

-- 

Daniel Goldberg, PhD
Lecturer in Glaciology
School of Geosciences, University of Edinburgh
Geography Building, Drummond Street, Edinburgh EH8 9XP


em: D <dgoldber at mit.edu>an.Goldberg at ed.ac.uk
web: http://ocean.mit.edu/~dgoldberg
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mitgcm.org/pipermail/mitgcm-support/attachments/20140311/8bea7587/attachment.htm>