Hello all,
I am trying to test my N-body (discussed in another post).
I am running the experiments on a bwlf cluster and they are taking too long.
For example:
# of PLACES : 1
07282013 12:46:24 : STARTED
input bodies: 120000
Time elapsed: 0.049372108
Time for initialisation: 8.72E-7
07292013 02:29:20 : FINISHED
So while the result runtime is really short and the total execution of the
program is 0.049373135
only this measurement run for almost 14 hours!!!
I am checking the cluster load and my processes are the following:
9789 pts/0 S+ 0:00 /bin/bash ./runfin2.sh --this is the script I am
running
9792 pts/0 S+ 0:00 /u1/msc/kp167/Desktop/x10/bin/X10Launcher
/usr/java/latest//bin/java -ea -Djava.library.path=/u1/msc/kp167/Deskto
9821 pts/0 S+ 0:00 /usr/bin/ssh -tt -q bwlf14 env
HOSTNAME"=${HOSTNAME-bwlf14}" TERM"=${TERM-xterm}"
SHELL"=${SHELL-/bin/bash}" ISAB
9825 pts/1 Ss+ 0:00 /u1/msc/kp167/Desktop/x10/bin/X10Launcher
/usr/java/latest//bin/java -ea -Djava.library.path=/u1/msc/kp167/Deskto
9829 pts/1 Sl+ 36:56 /usr/java/latest//bin/java -ea
-Djava.library.path=/u1/msc/kp167/Desktop/x10/lib -classpath
.:/u1/msc/kp167/Deskt
and with the top command I get only a sleeping command named java
My program does not wait for user input or reads files or anything like
that..it just initializes arrays using a random generator which takes
8.72E-7 time.
Can anyone tell me what is wrong??
Regards,
Konstantina
------------------------------------------------------------------------------
Get your SQL database under version control now!
Version control is standard for application code, but databases havent
caught up. So what steps can you take to put your SQL databases under
version control? Why should you start doing it? Read more to find out.
http://pubads.g.doubleclick.net/gampad/clk?id=49501711&iu=/4140/ostg.clktrk
_______________________________________________
X10-users mailing list
X10-users@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/x10-users
