Zorro, the AU High Performance Computing (HPC) System is managed by the HPC Liaison Committee; the policies on this page (download PDF) were developed by the Committee. The user policies below aim to
- help make the system effective for users,
- ensure proper maintenance of the system,
- document use of this federally-funded facility
- enable researchers to contribute to the system
This webpage always shows the policies currently in effect. Policies are continually reviewed and updated by the HPC Committee. Questions or concerns should be e-mailed to firstname.lastname@example.org.
It is key that all users have access to the HPC system and that the integrity of all users’ code is maintained. Following some of these policies is likely to require that you understand the nature of HPC computing and the configuration of the hardware and software on the system. Please contact email@example.com to ask questions or to report problems.
If a user does not abide by the policies, a representative of the HPC Liaison Committee has the right to terminate the user’s jobs and/or to suspend the user's account.
Users must use the batch submission system of the scheduler:
- Users may not log into the compute nodes for the purpose of running a job directly without permission from the HPC committee.
- If you believe interactive use of a node is necessary for your research please send a request to firstname.lastname@example.org.
Users must monitor the e-mail address on file with the HPC committee and are required to respond in a timely way to correspondence from the HPC Committee.
- Active communication is often necessary for effective management of a shared resource such as this HPC system.
- Users will be notified by e-mail about issues related to the system, such as scheduled downtime, upgrades, etc.
- Requests for information and feedback about system use and access will be made by e-mail.
Obtaining an Account
Costs of Use
There is no up-front cost for use of the American University HPC System. AU faculty PIs and students are encouraged to use the system to obtain preliminary results and to leverage their preliminary results into external funding (see Maintaining Access below). Externally funded users are encouraged to contribute funding to the facility. Users who provide financial support for the AU HPC System at the rate of $1000 per year will have 500 node-hours of priority access per month for 12 months, and a total guaranteed usage of one node-year for the year.
Who May Have An Account?
- Any AU faculty PI whose project has computational needs are beyond the capacity of his or her current workstation may apply for an account. The account can be accessed by all members of the research team on the project. (See Faculty Account Form.)
- Students (undergrad or grad) who are sponsored by an AU faculty PI to do independent research may apply for an account. (See Student Account Form.)
- Users from outside the AU community may also apply for an account for academic research, especially for research that includes an AU co-PI. The HPC Liaison Committee chair will be happy to assist in locating an AU co-PI. Please send inquiries to email@example.com.
The Chair of the HPC Liaison Committee reviews and approves requests for accounts continually. The Chair consults the Committee regarding special requests. User account status is reviewed annually by the Committee.
Accessing a User Account
There are three levels of access to the AU HPC System:
- High Priority (reserved for users who provide financial support for the AU HPC System, including the initial funding): Receive 500 node-hours each month for which the scheduler will put them at the front of the queue.
- Special Priority (reserved for Users whose special needs are approved by the HPC Committee): May request an allocation of node-hours each month for up to one year that will be put in the queue behind High Priority Users but in front of Normal Priority Users.
- Normal Priority (all other Users)
User access to compute nodes is managed by job scheduling software, called a scheduler, that reserves compute nodes for users. The scheduler reserves available compute nodes based on these guidelines:
- The scheduler reserves available nodes and other resources on a first-come-first-served basis among Users with equal priority.
- In general jobs are limited to no more than 23 node-hours. (That is, the product of the number of nodes requested times the number of hours to run the job is limited to be 23. Example 1: A serial job (1 node used) must complete within 23 hours. Example 2: If 23 nodes are used for the job, the length of the job will be limited to 1 hour.)
- The remaining hour of each day is reserved for running jobs that require a larger number of nodes than are available otherwise, if there are such requests in the queue. The scheduler is set up to pause all jobs and restart them within an hour or after all requests for large numbers of nodes are satisfied, whichever comes first.
- The above rules do not apply to system administration and testing of the machine.
Each user has an obligation to help to sustain the AU HPC System. While financial support will help grow the system, the most important way each user sustains the system is by demonstrating that it contributes to ongoing research.
- Acknowledge the use of the HPC system in papers and presentations. A recommended acknowledgement is "Computing resources used for this work provided by the American University High Performance Computing System, which is funded in part by the National Science Foundation (BCS-1039497); see www.american.edu/cas/hpc for information on the system and its uses."
- Confirm that user accounts are still needed when requested.
- Update Titles and Abstracts for each research project being conducted on the HPC system when requested. (Requests are planned to coincide with FARS due dates.)
- Provide information on presentations, working papers, and publications based on work using the HPC system. We are happy to post PDF files of papers or presentations on the facility's webpage or point a link to another webpage. (Requests for updates are planned to coincide with FARS due dates.)
- Be willing to participate as co-PI or co-investigator in future grant proposals in support of the HPC system (faculty users only).
- Include budget requests for computational resources in individual grant proposals. The support requested should reflect resource use expected for the project; use the cost per node for cited above is a guide. HPC Liaison Committee members and users will cheerfully assist with proposals in whatever way will be most helpful (including but not limited to: drafting text, acting as co-PI/co-investigator, supplying a letter of support). E-mail firstname.lastname@example.org early in your proposal process.
The HPC Liaison Committee manages the AU HPC System. New members will rotate onto the committee for two-year terms.
Contact the Committee at email@example.com.
Duties of the HPC Liaison Committee include:
- advising OIT and CTRL staff on decisions regarding setup, maintenance, and operations of HPC resources
- coordinating with OIT to monitor utilization of processing and storage capacity
- informing faculty (especially new faculty) and students about availability of HPC resources
- reviewing requests for priority use of shared HPC resources that might affect other users
- reviewing requests for storage of data files over the typical allocation
- reviewing requests to install new software; communicating concerns about system operations from researchers using the HPC resources to OIT and CTRL staff
- tracking outcomes of research projects completed using the HPC system
- reviewing requests for external access
- coordinating participation in SURAgrid
- coordinating training of users in parallel-capable code and applications;
- organizing a regular seminar to share research results, to encourage use of the system, and to foster interdisciplinary research.