The rates below represent cost recovery for the Great Lakes HPC Cluster and have been approved for use by those using the system for a fee. These rates do not include any support your unit may choose to provide.
For UMRCP users: as a reminder, be sure to set your jobs to use your UMRCP allocation whenever possible to avoid being unnecessarily charged. The rates below reflect costs for jobs run after the allocation is exhausted.
| Partition | Rate Per Minute | Rate Per Month | CPU Cores | Memory Unit | GPU Unit |
|---|---|---|---|---|---|
| standard/debug/viz | $0.000250463 | $10.82 | 1 | 7 GB | N/A |
| largemem | $0.000770370 | $33.28 | 1 | 41.75 GB | N/A |
| gpu | $0.002739120 | $118.33 | 20 | 90 GB | 1 |
| spgpu | $0.001807870 | $78.10 | 4 | 48 GB | 1 |
| gpu-rtx6000 | $0.003861015 | $166.80 | 16 | 192 GB | 1 |
| gpu_mig40 | $0.002739120 | $118.33 | 8 | 125 GB | 1 |
| Faculty Owned Equipment | $61.92 / node / month |
The monthly rate is based on a 30-day month; per-minute rates are included for reference. Charges are based on the percentage of the machine your job requests (in terms of the amount of cores, memory, and GPUs) and its actual runtime.
Estimating Maximum Job Costs
To calculate the cost of a job enter one of the commands below in Command Line. The estimated cost is based on CPU, memory, GPU, and partition selection. The amount returned is the most a job could cost and does not take into account any unit support or UMRCP allocations that you have available for use.
my_job_estimate --help
my_job_estimate --cores 20 --memory 10gb --partition standard
Other Unit Cost Sharing Information
Some units on campus provide additional funding in support of researchers for their units. Below are a list of links where you can find out if your college has additional funding you can leverage in your research: