Overview

Compute Resources

More detailed information on system resources can be found on our Compute Resources page.

Containers with GPU Support

Singularity containers are available as modules on HPC for GPU-supported workflows. For more information, see our documentation on Containers.

Accessing GPUs

Information on how to request GPUs using SLURM can be found in our SLURM Documentation.

Training

For a list of training resources related to GPU workflows, see our Training documentation.

Contents

Cluster Information

Puma

Puma has a different arrangement for GPU nodes than Ocelote and ElGato. Whereas the older clusters have one GPU per node, Puma has four. This has a financial advantage for providing GPU's with lower overall cost, and a technical advantage of allowing jobs that can use multiple GPU's to run faster than spanning multiple nodes. This capability comes from using a newer operating system.
Each node has four Nvidia V100S model GPUs. They are provisioned with 32GB memory compared to 16GB on the P100's.

Ocelote

Ocelote has 46 compute nodes with Nvidia P100 GPUs that are available to researchers on campus. The limitation is a maximum of 10 concurrent jobs. Previously, one node with a V100 was available, but it has since been replaced with a P100. Tasks which require multiple GPUs must either request multiple nodes on Ocelote, or use Puma's GPU nodes.

Cuda Modules

Nvidia Nsight Compute (the interactive kernel profiler) is not available. In response to a security alert (CVE-2018-6260) this capability is only available with root authority which users do not have.

The latest Cuda module available on the system is 11.8, with several older versions also available.The Cuda driver version can be queried with the nvidia-smi command. To see the modules available, in an interactive session simply run:

$ module avail cuda

-------------------- /opt/ohpc/pub/moduledeps/gnu8-openmpi3 ---------------------
   cp2k-cuda/7.1.0

--------------------------- /opt/ohpc/pub/modulefiles ---------------------------
   cuda11-dnn/8.0.2        cuda11-sdk/20.7         cuda11/11.0
   cuda11-dnn/8.1.1        cuda11-sdk/21.3         cuda11/11.2
   cuda11-dnn/8.9.2 (D)    cuda11-sdk/22.11 (D)    cuda11/11.8 (D)

OpenACC

The OpenACC API is a collection of compiler directives and runtime routines that allow you to specify loops and regions of code in standard C, C++, and Fortran that you can offload from a host CPU to the GPU.

We provide two methods of support for OpenACC

We support OpenACC in the PGI Compiler. The PGI implementation of OpenACC is considered the best implementation.
"module load pgi" on Ocelote. If you are on a GPU node from an interactive session you can run "pgaccelinfo" to test functionality. Remember that the login nodes do not have GPUs or software installed.
A useful getting-started guide written by Nvidia is available here: https://www.pgroup.com/doc/openacc17_gs.pdf
We support OpenACC in the GCC Compiler 6.1 which is automatically loaded as a module when you log into Ocelote. Verify with "module list".
The GCC 6 release includes a much improved implementation of the OpenACC 2.0a specification.
A useful quick reference guide is available from: https://gcc.gnu.org/wiki/OpenACC#Quick_Reference_Guide

GPU Nodes