You are viewing an old version of this page. View the current version.

Compare with Current View Page History

Version 1 Next »

Please note that the storage
system was modified, old $SCRATCH is available only on login01 node as a
readonly filesystem under the /net/ascratch/people/<login> directory. It will
be available until 28th of March.

$SCRATCH space is available in the location pointed by $SCRATCH variable,
group storage is available under the /net/pr2/projects/plgrid/<group name>
directory.

If you are using an account named aresXX, please create a proper PLGrid grant,
as aresXX temporary accounts will be disabled in the near future.

Please use the following commands for managing your accounts:
hpc-grants: shows available grants, resource allocations
hpc-fs: shows available storage
hpc-jobs: shows currently pending/running jobs
hpc-jobs-history: shows information about past jobs

Jobs should be submitted to plgrid, plgrid-long, plgrid-bigmem, plgrid-gpu and
other plgrid-* queues.

The standard partition is built with nodes containing 48 cores and 192 GB of
RAM, while the plgrid-bigmem contains nodes with 48 cores and 384 GB of RAM.
GPU partition contains nodes with 32 cores, 384 GB of memory and 8 NVIDIA Tesla
V100 GPUs.

  • No labels