Using large memory nodes on Hopper II
February 3, 2011 by Katie Antypas
The capability of explicitly requesting large memory nodes on Hopper II is now available.
Please see below the detailed information on Running Jobs: (also available on Hopper II web page):
Requesting Large-Memory Nodes 384 Hopper II compute nodes have 64 GB of memory, rather than the 32 GB found on most nodes. To request these large-memory nodes, use the Torque keyword mpplabels=bigmem:
#PBS -q debug
#PBS -l mppwidth=1024
#PBS -l mpplabels=bigmem
#PBS -l walltime=00:10:00
#PBS -N my_job
#PBS -e my_job.$PBS_JOBID.err
#PBS -o my_job.$PBS_JOBID.out
aprun -n 1024 ./my_executable
In this script, the user is requesting 43 nodes (1024 cores) that each contain 64 GB of memory. Note that it might take longer for such a job to start, as the batch system must wait for the desired nodes to become available. Please let us (firstname.lastname@example.org) know if you have any comments or questions.