Logo

HPC @ Uni.lu

High Performance Computing in Luxembourg

Specialized computing nodes (GPU and large memory nodes)

As of January 2019 the Iris cluster features GPU accelerated and large memory nodes. They are all based on Skylake-generation CPUs, and are divided in separate partitions:

Compute nodes Features SBATCH option sbatch/srun command line
iris-169..186 skylake,volta #SBATCH -p gpu sbatch -p gpu
iris-191..196 skylake,volta,volta32 #SBATCH -p gpu sbatch -p gpu
iris-187..190 skylake #SBATCH -p bigmem sbatch -p bigmem

Additional details can be found under our Slurm documentation page.

How to reserve large memory (bigmem) nodes under Slurm?

  • Interactive job with 0.5TB of RAM on 1 large memory node
    • one task will automatically be reserved with as many cores required in order to fulfill the Memory-per-Core ratio (at ~26GB RAM/core on large memory and GPU nodes)
1
srun -p bigmem -N 1 --mem=512G --pty bash -i
  • Submit a job script to the bigmem partition, requesting 64 cores and 2TB of RAM on a single node:
    • note that additional cores may be reserved for the job in order to preserve the Memory-per-Core ratio (at ~26GB RAM/core on large memory and GPU nodes)
1
sbatch -N 1 -n 1 -c 64 --mem=2T -p bigmem job.sh
  • Submit a job script to the bigmem partition, requesting the full node (112 tasks at 1 core/task and all associated RAM, ~3TB):
1
sbatch -N 1 -n 112 -p bigmem job.sh

Additional details can be found in the Slurm examples page.

Troubleshooting

Using GPUs