Am 26.08.2013 um 12:29 schrieb Bob Ilgner:

Dear all,

When adding #include "mpi.h" and building a single process with mpi, I find that the single process mpi job runs very much slower than a single thread process built with gcc. i.e. 150 to 200% slower, and run as a standalone executable.

That is, for example

gcc mycode.c -o mycode.exe ./mycode

will run in 100 seconds.

Adding #include "mpi.h" to mycode.c

mpicc mycode.c -o mycode.exe

`mpicc -showme ...` will show the options (and used compiler). Maybe the optimization options are set differently How fast is the application in case you start the Open MPI compilation without `mpirun` but just execute it in the usual way? -- Reuti

mpirun -n 1 mycode.exe

will take 180 to 400 seconds to run.

This varies from system to system on intel, Sparc or IBM based systems.

Can anyone explain this offhand ? Has anyone else experienced this ?

_______________________________________________ discuss mailing list [email protected] To manage subscription options or unsubscribe: https://lists.mpich.org/mailman/listinfo/discuss