[mpich-discuss] Program execution time:

PRATIK AGRAWAL pratik_9314 at yahoo.co.in
Tue May 18 04:46:24 CDT 2010


dear ...
your program execution time will always differ from previous execution.... 
the reason behind this is nothig but the system call/bus used by your program... It is impossible to make it constant for every execution .... 

if you get any way for making its execution time constant then please forward me....

Pratik AgrawalContact: +91-94287-63145Twitter: http://www/twitter.com/praxvoperhttp://www.pratikagrawal.x10.mx


--- On Sat, 15/5/10, sankar s <keanesankar at gmail.com> wrote:

From: sankar s <keanesankar at gmail.com>
Subject: [mpich-discuss] Program execution time:
To: mpich-discuss at mcs.anl.gov
Date: Saturday, 15 May, 2010, 5:52 PM

Hi,

I have developed a simulation program in c using MPI. I am using gettickcount() function to find time taken in each core for executing this program in a core2 duo processor.

start=gettickcount() ;
{

code
}
end=gettickcount();
time=end-start();

Its working properly but each time when I ran this code, its giving different execution times. its happening for my sequential code without MPI also. I am using Windows vista, DELL core 2 duo processor.


   Is there any way to measure exact execution time in c.Which will not change every time, when I run the program.?



Thanks
 


-----Inline Attachment Follows-----

_______________________________________________
mpich-discuss mailing list
mpich-discuss at mcs.anl.gov
https://lists.mcs.anl.gov/mailman/listinfo/mpich-discuss


-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.mcs.anl.gov/pipermail/mpich-discuss/attachments/20100518/edbea744/attachment.htm>


More information about the mpich-discuss mailing list