[Wien] lapw0_mpi for dual cores

[Michael Gurnett]

Thanks Peter

tested it manually like you recommended, and the following line worked

 mpiexec -machinefile /home/Michael/mpd.hosts -np 2 lapw0_mpi lapw0.def

and you were pretty close with the speed increase estimate (reduced the
time by 45%)

Thanks

Michael

On Sun, 2006-09-10 at 10:13 +0200, Peter Blaha wrote:
> Autoparallelization NEVER works reasonable (in my experience). Compilers 
> are still very bad in this respect. One would have to identify the time 
> consuming loops and put explicit parallelization statements into the code.
> 
> lapw0_mpi should reduce your time in lapw0 by about 40%.
> For mpi: How did you "configure WIEN" (parallel options in siteconfig),
> see also the file   $WIENROOT/parallel_options
> 
> Try to run lapw0_mpi "by hand". The exact command depends on your mpi, but 
> something like that should work:
> 
> mpirun -np 2 -hostfile machines lapw0_mpi lapw0.def
> 
> The file "machines" should contain two lines with the names of your dual 
> core pc.
> 
> On some mpi versions you need -machinefiles instead of -hostfile;
> or mpirun is called mpirun_ssh or similar.
> 
> Check your mpi:   
> which mpirun
> man mpirun
> or mpirun -h  (or --help),....
> 
> 
> > I've tried to compile using mpi (intels version) now. Seems to compile
> > fine, but I'm not able to run it. in my machines file I added lapw0:pc:2
> > 
> > in the mpd.hosts file I added 
> > pc
> > pc
> > 
> > If anyone has any experience with this it would be great
> > 
> > Michael 
> > 
> > On Sat, 2006-09-09 at 09:05 +0200, Michael Gurnett wrote:
> > > Tried that now, and the reulst is that with -parallel there is a 20
> > > second speed increase for a 44 min lapw0 run. So I would say the
> > > increase is quite insignificant. Still it was worth a try.
> > > 
> > > Michael
> > > 
> > > 
> > > On Fri, 2006-09-08 at 19:23 +0200, Gerhard H Fecher wrote:
> > > > Did you try to compile simply with the auto paralelliser:  -parallel 
> > > > 
> > > > I did not check it up to know but would be interesting if it speeds up on dual 
> > > > core machines without using special mpi libraries, what would be easier for 
> > > > unexperienced users.
> > > > 
> > > > Ciao
> > > > Gerhard
> > > > 
> > > > Am Freitag, 8. September 2006 18:29 schrieb Michael Gurnett:
> > > > > I've been checking the system monitor and it appears that even with
> > > > > OMP_NUM_THREADS=2 lapw0 really only using about 50% of the processing
> > > > > power of the dual cores. Has anyone tried using lapw0_mpi for a dual
> > > > > core, and was it easy to implement
> > > > > 
> > > > > 
> > > > > Thanks 
> > > > > 
> > > > > Michael
> > > > > 
> > > > > _______________________________________________
> > > > > Wien mailing list
> > > > > Wien at zeus.theochem.tuwien.ac.at
> > > > > http://zeus.theochem.tuwien.ac.at/mailman/listinfo/wien
> > > > > 
> > > > _______________________________________________
> > > > Wien mailing list
> > > > Wien at zeus.theochem.tuwien.ac.at
> > > > http://zeus.theochem.tuwien.ac.at/mailman/listinfo/wien
> > > > 
> > > 
> > > _______________________________________________
> > > Wien mailing list
> > > Wien at zeus.theochem.tuwien.ac.at
> > > http://zeus.theochem.tuwien.ac.at/mailman/listinfo/wien
> > > 
> > 
> > _______________________________________________
> > Wien mailing list
> > Wien at zeus.theochem.tuwien.ac.at
> > http://zeus.theochem.tuwien.ac.at/mailman/listinfo/wien
> > 
> 
> 
>                                       P.Blaha
> --------------------------------------------------------------------------
> Peter BLAHA, Inst.f. Materials Chemistry, TU Vienna, A-1060 Vienna
> Phone: +43-1-58801-15671             FAX: +43-1-58801-15698
> Email: blaha at theochem.tuwien.ac.at    WWW: http://info.tuwien.ac.at/theochem/
> --------------------------------------------------------------------------
> _______________________________________________
> Wien mailing list
> Wien at zeus.theochem.tuwien.ac.at
> http://zeus.theochem.tuwien.ac.at/mailman/listinfo/wien
>