Five steps
Tell us what you do
Your field, your data, and what you want to run. If you are not sure what you need, that is fine. Ask for a consultation.
Check your data
Find its protection level, and any agreement (data use, contract, IRB) attached to it. This decides where it can go.
Pick a service
Compare compute and storage options. Each service page says what it is for, what it is not for, and what it costs.
Get access
Follow the service's access steps. Usually your PI approves, an account is created, and a funding source is set up if the service carries a recharge.
Run and learn
Use the guides below and the knowledge base, and come to office hours when you get stuck.
The basics
- What is HPC?: what a cluster is and when it helps.
- Connecting to a cluster and running a first job.
- HPCC Linux basics: the command line essentials.
- Globus data transfer.
- HPCC users: the HPCC manuals cover login, Slurm, modules and storage on the cluster.
Workshops and courses
Research Computing and the HPCC run workshops from time to time; announcements go out on Slack. Good self-paced options:
- The Carpentries: Software, Data and Library Carpentry lessons on the shell, Git, Python and R.
- HPC Carpentry: introductory HPC lessons.
- Cornell Virtual Workshop: HPC and cloud topics, used across the national ACCESS community.
- ACCESS training and events: national webinars and workshops.
When you get stuck
Get help lists every way to reach us, office hours, and who handles which questions.