[QE-users] weird CPU and WALL time report
IORI, Federico
federico.iori at airliquide.com
Mon Feb 4 14:35:49 CET 2019
Hi all.
Sorry to bother by such a question but I found several times with version
6.3 a weird correspondence between CPU time and WALL time. (see attach
file reports)
For example in several runs I got at the end of my pw.out file
*PWSCF : 1h12m CPU 12h 1m WALL*
* 16h*
while the REAL wall time obtained as the difference between the starting
time on the header and the ending time at the bottom of the output file is
really 1h 12m in this case
It seems to me the numbers of the wall time are reversed wrt the CPU time
in the writing procedure.
I tried to find the routine printing this last PWSCF line but I cannot find
it.
My questions:
1) is normal this behaviour?
2) does someone already noted it ?
3) should I start to worry about my compilation ?
4) can you tell me how is called such routine printing the PWSCF execution
time?
Thanks for now!
With the best
--
Federico IORI
Computational material scientist
Paris-Saclay Research Center
1 chemin de la Porte des Loges
<https://www.google.com/maps/place/Air+Liquide/@48.8297381,2.2016685,11.75z/data=!4m5!3m4!1s0x47e67e61a4fbbdc7:0xca3bea9e80059880!8m2!3d48.7630415!4d2.1333045>
Les Loges en Josas – 78354 Jouy en Josas cedex
Mail: federico.iori at airliquide.com
Phone: +33 7 621 605 15
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.quantum-espresso.org/pipermail/users/attachments/20190204/10dfc988/attachment.html>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: header_out
Type: application/octet-stream
Size: 859 bytes
Desc: not available
URL: <http://lists.quantum-espresso.org/pipermail/users/attachments/20190204/10dfc988/attachment.obj>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: time_report_out
Type: application/octet-stream
Size: 3994 bytes
Desc: not available
URL: <http://lists.quantum-espresso.org/pipermail/users/attachments/20190204/10dfc988/attachment-0001.obj>
More information about the users
mailing list