Unity Partitions
| General Access | Partition | # Nodes | Maximum Time Limit | Default Time Limit | Limits | Notes |
|---|---|---|---|---|---|---|
check | arm-gpu | 4 | 5 days | 1 hour | 2 nodes per user | |
check | arm-preempt | 3 | 5 days | 1 hour | ||
check | cpu | 186 | 5 days | 1 hour | 512 cores per PI group | |
check | cpu-preempt | 169 | 5 days | 1 hour | ||
check | gpu | 131 | 5 days | 1 hour | 64 GPUs per PI group | |
check | gpu-highvram | 23 | 5 days | 1 hour | 16 GPUs per PI group, 8 GPUs per user | |
check | gpu-preempt | 167 | 5 days | 1 hour | 64 GPUs per PI group | |
check | gpu-preempt-highvram | 44 | 5 days | 1 hour | 16 GPUs per PI group, 8 GPUs per user | |
check | mpi | 25 | 5 days | 1 hour | 4 nodes per user | |
check | power9 | 2 | 5 days | 1 hour | ||
check | power9-gpu | 16 | 5 days | 1 hour | ||
check | power9-gpu-preempt | 16 | 5 days | 1 hour | ||
| arm | 9 | 5 days | 1 hour | |||
| astroth-cpu | 8 | 5 days | 1 hour | |||
| astroth-gpu | 3 | 5 days | 1 hour | |||
| cbio-cpu | 5 | 5 days | 1 hour | |||
| cbio-gpu | 1 | 5 days | 1 hour | |||
| ceewater_casey-cpu | 10 | 5 days | 1 hour | |||
| ceewater_cjgleason-cpu | 10 | 5 days | 1 hour | |||
| ceewater_kandread-cpu | 10 | 5 days | 1 hour | |||
| ece-gpu | 2 | 5 days | 1 hour | |||
| fsi-lab | 1 | 5 days | 1 hour | |||
| gaoseismolab-cpu | 5 | 5 days | 1 hour | |||
| superpod-a100 | 12 | 5 days | 1 hour | |||
| gpupod-l40s | 14 | 5 days | 1 hour | |||
| gpupod-h200 | 1 | 5 days | 1 hour | |||
| gpupod-rtx6000_2g.48gb | 1 | 5 days | 1 hour | |||
| ials-gpu | 28 | 5 days | 1 hour | |||
| jdelhommelle | 1 | 5 days | 1 hour | |||
| lan | 1 | 5 days | 1 hour | |||
| ood-shared | 5 | 8 hours | 1 hour | |||
| toltec-cpu | 7 | 5 days | 1 hour | |||
| umd-cscdr-arm | 3 | 5 days | 1 hour | |||
| umd-cscdr-cpu | 35 | 5 days | 1 hour | |||
| umd-cscdr-gpu | 10 | 5 days | 1 hour | |||
| uri-cpu | 49 | 5 days | 1 hour | 768 cores per PI group | ||
| uri-gpu | 11 | 5 days | 1 hour | 16 GPUs per PI group | ||
| visterra | 7 | 5 days | 1 hour | |||
| workflow | 5 | 5 days | 1 hour | |||
| zhoulin-cpu | 6 | 5 days | 1 hour |
Notes
- Restricted to members of CSCDR at UMass Dartmouth.
- Restricted to users affiliated with the University of Rhode Island.
- Nodes have the ARM architecture, most software and modules will not work unless built for ARM.
- Nodes have the POWER9 architecture, most software and modules will not work unless built for POWER9.
- Nodes in preempt partitions belong to specific groups which would normally be inaccessible to general users. Priority users reserve the right to kill (preempt) any job running on their nodes to make room for their own jobs. When you schedule a job on a preempt partition, your job can be killed after two hours.
- See the mpi partition page for details.
Some partitions have their own documentation page for details on the nodes and best practices, such as the mpi partition.
Last modified: Thursday, November 5, 2026 at 12:12 PM. See the commit on GitLab.