In response to the growing demand for high-performance computing (HPC) resources for use with sensitive data, the SoM Research Computing Center (SRCC) was established in February 2024 on behalf of the Duke School of Medicine. As a Service Center, we operate under a cost-recovery model for both cloud and on-premises based services that ensures cost-competitive rates, equitable access to our services, and aligns with federal agreements that govern Facilities and Administration (F&A) rates.
Please contact the SoM Research Computing Center (SRCC) to determine the option that best meets the needs of your research group.
Pay for play is a resource consumption charge that covers the cost of provisioned resources such as compute and storage. All cloud services are usage-based. Usage charges:
- Depend on the amount and type of resources requested.
- Can be paid for by grants, start-up funds, or by departmental funds.
- Require a fund code for all HPC requests.
- Do NOT include Facilities & Administrative (F&A) cost
If unsure about your source of funding, please contact your CRU or departmental business manager. CRUs and OOs | Duke University School of Medicine
On-Premises Rates
| SoM HPC | Price per Unit |
|---|---|
| SoM HPC CPU | $0.07 per hour |
| SoM HPC GPU | $3.50 per hour |
| SoM HPC Storage : Home Directories | Free up to 50GB quota |
| SoM HPC Storage : Scratch Space | Free up to 10TB* per account |
*Please contact SRCC to request additional storage
DASH Rates on Azure
| HPC DASH (Cloud) | Price per Unit |
|---|---|
| HPC Cloud Standard CPU | $2.30 per hour |
| HPC Cloud Premium CPU | $3.20 per hour |
| HPC Cloud Standard GPU | $3.67 per hour |
| HPC Cloud Premium GPU | $7.35 per hour |
| HPC Cloud Storage (Lustre*) | $0.60 per GB per month |
*Please contact SRCC for Azure Blob or other Azure storage options
HPC Support
| HPC Support | Support per hour |
|---|---|
| Consulting | $140.00 |
Note – Billing rates were last updated on Feb. 1, 2024, and are reviewed and updated annually
Departments and units can pre-pay an annual rate to subsidize and/or cover costs for researchers for a pre-determined amount of compute hours and storage, as well as for a pre-determined number of advanced technical support and/or software engineering hours.
The rates are the same rates that apply for individual compute and storage usage. The annual subscription is beneficial for departments who have academic program requirements for students or for new researchers.
Primary Investigators, departments and units have the option to contribute to the HPC on-premises cluster by paying for the full cost of the hardware and a one-time setup fee up front and then pay annual support costs. Hardware can include servers, GPUs, and/or storage.
The SRCC can work with approved vendors to provide you options that meet your budget and requirements.
COMING SOON: list of recommended options and pricing for purchase of additional compute and storage hardware.
Billing and Invoice Details
Billing for the use of these services started in March 2024. Invoices are issued monthly.
Charges for both on-premise and cloud based HPC will be reflected on the same invoice for each account/fund code.
When submitting a job, billing is based on the time your job takes and the resources you requested.
For example, if a job requests one core for 10 hours but only runs for 5 hours, the charge will be for the 5 hours of actual run time.
TIP: for jobs with large datasets, it is recommended to test jobs first and refine pipelines with a subset of the data in order to save costs.
Each fund code’s invoice will detail:
- Compute: in CPU hours
- Storage: in bytes and converted to GB
- Services: hourly rates