Hi all,
Could anyone explain all the meanings of these columns in log?
I'd appreciate your help.
Domain decomp.
DD comm. load
DD comm. bounds
Send X to PME
Neighbor search
Comm. coord.
Force
Wait + Comm. F
PME mesh
PME wait for PP
Wait + Recv. PME F
NB X/F buffer ops.
Write traj.
Update
Constraints
Comm. energies
Rest
------------------
Total
------------------
------------------
PME redist. X/F
PME spread/gather
PME 3D-FFT
PME 3D-FFT Comm.
PME solve
于2014年7月28日 15:51:15,Guillaume Chevrot写到:
Hi,
if you need 0.345 hour to get 1 ns, that means that you can simulate
1/0.345~2.9ns/hour, then in one day you will simulate 1/0.345*24~69.5 ns
Guillaume
On 07/28/2014 09:39 AM, Theodore Si wrote:
I thought that 69.479 ns/day means I can simulate 69.479 ns per day.
But if as you said, I need 0.345 hour to get a simulated nanosecond,
then I can only get 0.345 * 24 = 8.28 simulated nanosecond per day?
Then what does 69.479 mean? And the Core t(s)?
于 2014/7/28 15:29, Mark Abraham 写道:
Your run took nearly a minute, and did so at a rate that would take
0.345
hours to do a simulated nanosecond
Mark
On Mon, Jul 28, 2014 at 9:05 AM, Theodore Si <sjyz...@gmail.com> wrote:
Core t (s) Wall t (s) (%)
Time: 2345.800 49.744 4715.7
(ns/day) (hour/ns)
Performance: 69.479 0.345
What does 0.345 hour/ns stand for? and the Wall time 49.77s?
于 2014/7/28 14:53, Mark Abraham 写道:
I plan to put some more of this kind of documentation in the
upcoming User
Guide, but it isn't done yet.
Number of times that section was entered, the total wall time
spent in
that
section, and the total number of processor gigacycles spent in that
section, and percentage of same. Some columns are useful for only
some
kinds of comparisons.
Mark
On Mon, Jul 28, 2014 at 5:35 AM, Theodore Si <sjyz...@gmail.com>
wrote:
Thanks a lot!
But I am still confused about other things.
For instance, what do count, wall t(s) G-Cycles mean? It seems
that the
last column is the percentage of G-Cycles.
I really hope there is a place where I can find all relative
information
of the log file.
于 2014/7/28 11:12, Mark Abraham 写道:
On Jul 28, 2014 4:53 AM, "Theodore Si" <sjyz...@gmail.com> wrote:
For example, in the following form, what does Wait + Comm. F
mean? Is
there a webpage that explains the forms in log file?
Unfortunately not (yet), but they correspond in a
more-or-less clear
way
to
the segments in manual figure 3.16. In this case, to the three
boxes
below
"Evaluate potential/forces." Significant time spent here would
indicate
poor balance of compute load.
Mark
R E A L C Y C L E A N D T I M E A C C O U N T I N G
Computing: Nodes Th. Count Wall t (s) G-Cycles %
------------------------------------------------------------
-----------------
Domain decomp. 24 2 801 2.827 351.962 5.7
DD comm. load 24 2 800 0.077 9.604 0.2
DD comm. bounds 24 2 800 0.354 44.014 0.7
Neighbor search 24 2 801 1.077 134.117 2.2
Launch GPU ops. 24 2 40002 1.518 189.021 3.1
Comm. coord. 24 2 19200 2.009 250.121 4.0
Force 24 2 20001 8.478 1055.405 17.0
Wait + Comm. F 24 2 20001 1.967 244.901 4.0
PME mesh 24 2 20001 24.064 2995.784 48.4
Wait GPU nonlocal 24 2 20001 0.170 21.212 0.3
Wait GPU local 24 2 20001 0.072 8.935 0.1
NB X/F buffer ops. 24 2 78402 0.627 78.050 1.3
Write traj. 24 2 2 0.037 4.569 0.1
Update 24 2 20001 0.497 61.874 1.0
Constraints 24 2 20001 4.198 522.645 8.4
Comm. energies 24 2 801 0.293 36.500 0.6
Rest 24 1.478 184.033 3.0
------------------------------------------------------------
-----------------
Total 24 49.744 6192.746 100.0
------------------------------------------------------------
-----------------
------------------------------------------------------------
-----------------
PME redist. X/F 24 2 40002 6.199 771.670 12.5
PME spread/gather 24 2 40002 7.194 895.557 14.5
PME 3D-FFT 24 2 40002 2.727 339.480 5.5
PME 3D-FFT Comm. 24 2 80004 7.460 928.742 15.0
PME solve 24 2 20001 0.434 53.968 0.9
------------------------------------------------------------
-----------------
--
Gromacs Users mailing list
* Please search the archive at
http://www.gromacs.org/Support/Mailing_Lists/GMX-Users_List before
posting!
* Can't post? Read http://www.gromacs.org/Support/Mailing_Lists
* For (un)subscribe requests visit
https://maillist.sys.kth.se/mailman/listinfo/gromacs.org_gmx-users
or
send a mail to gmx-users-requ...@gromacs.org.
--
Gromacs Users mailing list
* Please search the archive at http://www.gromacs.org/
Support/Mailing_Lists/GMX-Users_List before posting!
* Can't post? Read http://www.gromacs.org/Support/Mailing_Lists
* For (un)subscribe requests visit
https://maillist.sys.kth.se/mailman/listinfo/gromacs.org_gmx-users or
send a mail to gmx-users-requ...@gromacs.org.
--
Gromacs Users mailing list
* Please search the archive at http://www.gromacs.org/
Support/Mailing_Lists/GMX-Users_List before posting!
* Can't post? Read http://www.gromacs.org/Support/Mailing_Lists
* For (un)subscribe requests visit
https://maillist.sys.kth.se/mailman/listinfo/gromacs.org_gmx-users or
send a mail to gmx-users-requ...@gromacs.org.
--
Gromacs Users mailing list
* Please search the archive at
http://www.gromacs.org/Support/Mailing_Lists/GMX-Users_List before posting!
* Can't post? Read http://www.gromacs.org/Support/Mailing_Lists
* For (un)subscribe requests visit
https://maillist.sys.kth.se/mailman/listinfo/gromacs.org_gmx-users or send a
mail to gmx-users-requ...@gromacs.org.
