[Wien] k point parallel mode

susanta mohanta susanta.phy at gmail.com
Fri Dec 30 13:10:52 CET 2011


Thanks for this suggestions. I am using ifort (version 12 update 3) and
mkl. i am trying to make the .machine file
for k point parallel mode and inform you if any problem persists.

On Fri, Dec 30, 2011 at 5:32 PM, Laurence Marks <L-marks at northwestern.edu>wrote:

> A comment on Peter''s comment. OMP_NUM_THREADS might have an effect,
> but the parameter is really MKL_NUM_THREADS if you are using Intel's
> mkl library -- and even then the compiler makes it's own decisions
> about how many it will use and this varies with version of the
> compiler (and probably what one has to set).
>
> Also...many of these things depend upon exactly what is in your
> computer, e.g. memory speed, bus speed as well as what else is
> running. Best is to do your own benchmarks, e.g. see
> http://www.wien2k.at/reg_user/benchmark/. For instance, while on older
> computers Intel's hyperthreading was not good much to my surprise when
> I tried it (by accident) on a recent dual hex-core machine it was
> quite reasonable.
>
> N.B., the same holds for mpi -- very hardware and software dependent
> in my experience.
>
> On Fri, Dec 30, 2011 at 5:44 AM, Peter Blaha
> <pblaha at theochem.tuwien.ac.at> wrote:
> >> To "make" the file, you use an editor (nothing more or less) and putthe
> >> file in the directory where you are running the job. I have notlooked,
> but
> >> there is probably something in w2web to do this.
> >> N.B., the code does not use OMP anywhere (at present) so this will notdo
> >> anything.
> >
> >
> > Just a small correction: If you are using the mkl, OMP_NUM_THREADS will
> have
> > an
> > effect in the diagonalization part of lapw1 (which is often the main part
> > anyway).
> >
> > However, while OMP_NUM_THREADS = 2 is quite effective and speeds up the
> > diagonalization
> > significantly, =4 is far less efficient and = 6 is usually useless.
> >
> > PS: On a 6 core machine you should run ONLY 6 jobs at the same time (or 3
> > k-parallel
> > jobs with OMP_NUM_THREADS=2) !!!
> > Intels "hyperthreading", which mimics "12 processors" to you, should
> even be
> > switched
> > off (BIOS), because it will slow down the jobs.
> >
> >
> >
> > --
> > -----------------------------------------
> > Peter Blaha
> > Inst. Materials Chemistry, TU Vienna
> > Getreidemarkt 9, A-1060 Vienna, Austria
> > Tel: +43-1-5880115671
> > Fax: +43-1-5880115698
> > email: pblaha at theochem.tuwien.ac.at
> > -----------------------------------------
> > _______________________________________________
> > Wien mailing list
> > Wien at zeus.theochem.tuwien.ac.at
> > http://zeus.theochem.tuwien.ac.at/mailman/listinfo/wien
>
>
>
> --
> Professor Laurence Marks
> Department of Materials Science and Engineering
> Northwestern University
> www.numis.northwestern.edu 1-847-491-3996
> "Research is to see what everybody else has seen, and to think what
> nobody else has thought"
> Albert Szent-Gyorgi
> _______________________________________________
> Wien mailing list
> Wien at zeus.theochem.tuwien.ac.at
> http://zeus.theochem.tuwien.ac.at/mailman/listinfo/wien
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://zeus.theochem.tuwien.ac.at/pipermail/wien/attachments/20111230/af7a9246/attachment.htm>


More information about the Wien mailing list