<GREETING>

Below are jobs that ran on an A100 GPU on Della in the past <DAYS> days:

<TABLE>

GPU-Mem-Used-Max is the maximum GPU memory usage of the individual allocated
GPUs while CPU-Mem-Used/GPU is the total CPU memory usage of the job divided by
the number of allocated GPUs.

The jobs above have a low GPU utilization and they use less than 10 GB of GPU
memory and less than 32 GB of CPU memory. Such jobs could be run on the MIG
GPUs. A MIG GPU has 1/7th the performance and memory of an A100. To run on a
MIG GPU, add the "partition" directive to your Slurm script:

   #SBATCH --nodes=1
   #SBATCH --ntasks=1
   #SBATCH --cpus-per-task=1
   #SBATCH --gres=gpu:1
   #SBATCH --partition=mig

For interactive sessions use, for example:

   $ salloc --nodes=1 --ntasks=1 --time=1:00:00 --gres=gpu:1 --partition=mig

If you are using Jupyter OnDemand then set the "Node type" to "mig" when
creating the session.

As an alternative to MIG, you may consider trying to improve the GPU
utilization of your code. A good target value is greater than <TARGET>%. Consider
writing to the mailing list of the software that you are using or attend
an in-person Research Computing help session:

   https://your-institution.edu/support/help-sessions

For general information about GPU computing:

   https://your-institution.edu/KB/gpu-computing

Replying to this automated email will open a support ticket with Research
Computing.
