[Wien] Error in mpi+k point parallelization across multiple nodes

[Gavin Abo]

On page 131 in the User's Guide for Intel mkl 11.1 for Linux [ 
https://software.intel.com/en-us/mkl_11.1_ug_lin_pdf ], it has:

libmkl_blacs_intelmpi_lp64.so => LP64 version of BLACS routines for 
Intel MPI and MPICH2

So -lmkl_blacs_intelmpi_lp64 might also work with MPICH2.

 From the compile settings, it looks like compiler version 11.1 build 46 
is being used, which uses version 10.2 Update 2 of mkl [ 
https://software.intel.com/en-us/articles/which-version-of-ipp--mkl--tbb-is-installed-with-intel-compiler-professional-edition 
].

I could not find the mkl system requirements page for 10.2, but for 
10.3, it has that 10.3 was validated with MPICH2 version 1.3.2p1 [ 
https://software.intel.com/en-us/articles/intel-mkl-103-system-requirements 
].

The MVAPICH2-2.0a that was mentioned as being used is based on 
MPICH-3.0.4 [ 
http://mvapich.cse.ohio-state.edu/static/media/mvapich/MV2_CHANGELOG-2.1.txt 
].

It looks like Intel did not validate MPICH3 until about mkl version 11.2 
with MPICH3 version 3.1 [ 
https://software.intel.com/en-us/articles/intel-mkl-112-system-requirements 
].

Fermin, it looks like you provided information from the WIEN2k dayfile 
and error files.  However, are there any error messages in the standard 
output?  For example, standard output should be what you get in a 
terminal after you execute "runsp_lapw -p". However, since clusters 
typically require that calculations be submitted using a job submission 
system, the standard output is usually written instead to a user 
specified file.  On some systems, for example, the calculation isn't 
executed with "runsp_lapw -p" but with "qsub -j oe -o output.log 
myscript.pbs" [ http://arc.it.wsu.edu/UserGuide/Using_Qsub.aspx ], where 
the script file called myscript.pbs would contain a line to execute 
"runsp_lapw -p"  and the standard output would be written to the file 
called output.log.

On 5/4/2015 12:08 AM, Peter Blaha wrote:
> No !!! (Can use it only if you are using intelmpi).
>
> I'm not sure (and it may even depend on the compiler version) which
> mpi-versions are supported by intel. But maybe try the simplest version
> -lmkl_blacs_lp64
>
> Am 04.05.2015 um 08:03 schrieb lung Fermin:
>> Is it ok to use -lmkl_blacs_intelmpi_lp64?
>