[Pw_forum] newbie update

[Carlo Nervi]

Dear all,
finally I succesfully compiled the code using ifort, mkl
and mpich2.
However, I'm getting odd results, very probably due to
wrong settings.

I tried to run the example01 with the following settings:

OMP_NUM_THREADS=1
mpiexec -n 8

The example is executed, but with a very long time. All 8
CPUs are running
between 5 and 20 % of the cpu time. For some reason we are
not using all the power..
I tried to run also "mpiexec -envall -n 8" (maybe the
OMP_NUM_THREADS is not passed)
but i got identical results.
Here is the results of the first example in the example01
directory:

results/si.scf.david.out

     Writing output data file silicon.save

     PWSCF        :     0.50s CPU time,    7.27s wall time

On the other hand, if I set

OMP_NUM_THREADS=8
and do not use mpiexec I got:

     Writing output data file silicon.save

     PWSCF        :     7.10s CPU time,    1.12s wall time

Therefore results/si.scf.david.out takes 1.12s instead of
7.27s, a much
more reasonable timing.
Anyone could give me an advice?
Thank you,
  Carlo

--
------------------------------------------------------
Carlo Nervi carlo.nervi at unito.it Tel:+39 011 6707507/8
Fax: +39 011 6707855 - Dipartimento di Chimica IFM
via P. Giuria 7, 10125 Torino, Italy
http://lem.ch.unito.it/