Welcome!

This site provides details of IT-supported hardware and software environments, instructions and tutorials on their use, and their organizational and administrative structure for the IT Research Computing community clusters. These community clusters are supported by the IT HPC Team.

To view all of the specific system information for active clusters including individual nodes and system status, see UD IT HPC.

The table below lists community clusters currently in service and supported by the IT HPC Team. The cluster documentation pages will have system information, a getting started guide, and specific documentation for that cluster. Visit the cluster specification pages for specific cluster configuration information.

The table below lists NSF funded HPC resources available via committee reviewed allocation request process similar to ACCESS (XSEDE) allocations.

This wiki includes several types of instructional documentation

• Instructions specific to each cluster such as system overview and specifications, getting started, transferring files, installing software, and running jobs can be found on the sidebar for each cluster.

• The software-specific area contains local documentation that augments vendor-supplied documentation for application software.

• The technical documentation area contains information authored by IT-NSS and IT-CSS as the HPC systems are built. This information is published to aid IT staff with future cluster deployments and to aid others who are building HPC systems.

In this wiki, the notational convention «name» indicates a placeholder whose value you supply. (You do not type the "«" or "»" symbols.)

Also Unix commands or commands specific to our cluster environment will be bolded, and defined terms specific to our cluster will be italicized.

To use the compute nodes for a particular investing-entity cluster group (workgroup), you need to use the workgroup command.

workgroup -g «investing-entity»

For example, to start a new shell for the workgroup (investing-entity) it_css, type

    workgroup –g it_css

If you are experiencing a problem on one of the UD HPC clusters (such as problems with disk quotas, nodes' being offline or malfunctioning, and requests for IT RCI provisioning of software), or you just can't find the help you need on this wiki, then submit a Research Computing High Performance Computing (HPC) Clusters Help Request and complete the form including which cluster and your problem details in the description field. This will generate a TeamDynamics ticket that is automatically routed to IT RCI staff.

hpc-ask is a Google group established to stimulate interactions within UD’s broader HPC community and is based on members helping members. This is a great venue to post a question about HPC, start a discussion or share an upcoming event with the community. Keep in mind posting a question is seeking assistance from other HPC users in the community like problems with installing software, integrating it with Slurm, or executing it; when no answer is forthcoming from the community, IT RCI tend to field the questions. Equally pertinent would be asking the community for recommendations of algorithms or software to solve a specific problem, or posting an upcoming event. These issues can be fielded by any member of the HPC community. Anyone may request membership. Messages are sent as a daily summary to all group members. This list is archived, public, and searchable by anyone.

If you are unsure which forum is the appropriate choice, please default to opening a TeamDynamics ticket by submitting a Research Computing High Performance Computing (HPC) Clusters Help Request.

For general acknowledgment of UD IT-RCI staff and HPC resources, please use the following text: "This research was supported in part through the use of Information Technologies (IT) resources at the University of Delaware, specifically the high-performance computing resources."

For Caviness and Farber, HPC templates are available to use for a proposal or publication to acknowledge use of or describe UD’s Information Technologies HPC resources.

For DARWIN, please refer to the NSF award information for a proposal or publication to acknowledge use of or describe DARWIN resources. We require all allocation recipients to acknowledge their allocation awards using the following standard text: “This research was supported in part through the use of DARWIN computing system: DARWIN – A Resource for Computational and Data-intensive Research at the University of Delaware and in the Delaware Region, Rudolf Eigenmann, Benjamin E. Bagozzi, Arthi Jayaraman, William Totten, and Cathy H. Wu, University of Delaware, 2021, URL: https://udspace.udel.edu/handle/19716/29071″