- Infos im HLRS Wiki sind nicht rechtsverbindlich und ohne Gewähr -

Difference between revisions of "NEC Cluster Using MPI"

From HLRS Platforms
Jump to navigationJump to search
(21 intermediate revisions by 3 users not shown)
Line 1: Line 1:
== Intel MPI example ==
=== OpenMPI ===
As Nehalem system is a twosocket system with local attached ccNUMA memory,
see [[Open MPI]]
memory and process placmeent can be crucial.
Here is an example that shows a 16 node Job, using 1 process per socket and 4 threads
=== Intel MPI ===
per socket and optimum NUMA placement of processes and memory.
Prerequiste: Use intel MPI and best intel compiler
see [[Intel MPI]]
To setup environment for this, use this .modulerc file in your home:
=== MVAPICH2 ===
set version 1.0
module load compiler/intel/11.0
module load mpi/impi/intel-11.0.074-impi-
And compile your application using mpicc/mpif90.
see [[MVAPICH2]]
First step: Batch submit to get the nodes
=== MPI I/O ===
  qsub -l nodes=16:nehalem:ppn=8,walltime=6:00:00 -I          # get the 16 nodes
see [[MPI-IO]]
Second step: make a hostlist
  sort -u  $PBS_NODEFILE  > m
Third step: make a process ring to be used by MPI later
mpdboot  -n 16 -f m -r ssh 
Fourth step: start MPI application
mpiexec -perhost 2 -genv I_MPI_PIN 0  -np 32 ./wrapper.sh ./yourGloriousApp
With wrapper.sh looking like this
export KMP_AFFINITY=verbose,scatter
if [ $(expr $PMI_RANK % 2) = 0  ]
        export GOMP_CPU_AFFINITY=0-3
        numactl --preferred=0 --cpunodebind=0 $@
        export GOMP_CPU_AFFINITY=4-7
        numactl --preferred=1 --cpunodebind=1 $@
Result is an application running on 16 nodes, using 32 processes spawning
128 threads. One set of 4 therads is pinned to the one socket, the other set of 4 threads to the other socket.

Latest revision as of 14:44, 12 June 2013


see Open MPI

Intel MPI

see Intel MPI




see MPI-IO