[mpich-discuss] A few inconveniences with MPICH 3.3 build

Balaji, Pavan balaji at anl.gov
Wed Feb 13 05:58:28 CST 2019


Martin,

For the slurm question, no you don't need to configure with slurm to get the nodelist.  You only need it if you want to use srun directly.  The recommended option is to use mpiexec directly (like you normally would).  mpiexec will internally lose srun anyway, and it'll automatically detect the nodes that you allocated in slurm (e.g., through salloc).

Adding slurm to configure allows you to use slurm's PMI, which is just internal MPICH-speak.  You probably won't need to care about that.

  -- Pavan

> On Feb 12, 2019, at 11:15 PM, Martin Cuma via discuss <discuss at mpich.org> wrote:
> 
> Thanks Brice for the tip, after some digging I found the appropriate spot to put these two options (enable_gl=no, enable_opencl=no) to src/pm/hydra/configure.
> 
> MPICH developers - any chance this can be wrapped around the --without-x configure option, or hardcoded?
> 
> Any takers on the SLURM question?
> 
> Thanks,
> MC
> 
> -- 
> Martin Cuma
> Center for High Performance Computing
> Department of Geology and Geophysics
> University of Utah
> 
> _______________________________________________
> discuss mailing list     discuss at mpich.org
> To manage subscription options or unsubscribe:
> https://lists.mpich.org/mailman/listinfo/discuss




More information about the discuss mailing list