Shared Computing Environment
FarmShare, Stanford’s shared computing environment, is intended for use in coursework and unsponsored research by anyone with a full-service SUNet ID.
Resources on FarmShare are focused on making it easier to learn how to use research computing, including “scheduler” or “distributed resource management system” to submit compute jobs. By using FarmShare, new researchers can more easily adapt to using larger clusters when they have big projects that involve using federally funded resources, shared Stanford clusters, or a small grant-funded cluster.
Environments
There are three environments available, each with a separate purpose. All machines currently run the Ubuntu operating system and are updated regularly.
- Login nodes, called rice servers, are where you log in to run commands, access files, submit jobs, and review results. The rice servers also have access to Stanford AFS. These servers can be accessed via
ssh
and be used for interactive work. Some resource limits are enforced, so if you need to run a long-running or compute- and/or memory-intensive process, you should submit a job. - Compute nodes are referred to as iron, rye, and wheat servers. They have more CPU power and more memory than the rice servers, and are meant for both interactive jobs (where you log in to control what happens) and batch jobs (where everything runs from a script that you submit.)
- GPU compute nodes are called oat servers. They are similar to the compute nodes mentioned above, except that they also have GPUs installed.
FarmShare currently has four rice servers (login nodes) and 26 compute nodes (iron, rye, wheat, and oat nodes). User storage for $HOME
, along with global /scratch
space, is available on all nodes.
Features
- Supports a number of different types of computing tasks
- Maintains locally installed software on each machine.
- Provides a selection of software, including a number of popular licensed applications.
- Supports long-running, multi-day jobs.
- Supports parallel processing (via MPI or OpenMP).
- Slurm is available for job (resource) management.
- Has browser-based access with Open OnDemand v4.
- Includes Ondemand apps JupyterLabs, RStudio, and VS Code.
Designed for
Current faculty, staff, and students
Requirements
- A full-service SUNet ID
- A computer with a program that provides SSH capability
Data security
- May not be used to transmit, store, or compute with Low Risk, or Moderate Risk, as defined by the Information Security Office.
- See Secure AFS for secure storage, but please note that FarmShare systems do not support processing or manipulating data in Secure AFS storage.
Rates
Free of charge
Get started
Users are required to connect remotely. See the Getting Connected webpage for instructions.
Get help
- Submit a Help Ticket to the Research Computing team.
- For email support, send a message to srcc-support. Ensure that “FarmShare” is included in the subject line, and please provide as much detail as possible with your request.