The introduction of research core services allows us a way to recoup some of the cost associated with the services we offer.  For solicitations that can accommodate these costs in a budget line, please consider including them in your future proposals.  Until you can use award monies to purchase the services, free voucher credits can be applied for.

Research Computing Units

The currency of the research computing vouchers is measured in Research Computing Units.  The value of 1 RCU is based on a common vHPC measure of 1 CPU-Hour. So, 1 RCU = $0.03.

Basic Vouchers

Basic Voucher are for 50,000 RCUs ($1,667) and their terms are based on the type of project:

  • Course-based student work (1-semester)
  • Student-based research (1-year)
  • Discovery, exploratory and limited computation (1-year)

For the vHPC, there is a reduced priority for voucher-based accounts.  Voucher accounts are not preempted by accounts with a funding source, but a funded account job can jump the wait queue in front of a similar job from a voucher account.

Voucher based accounts also have a lower amount for concurrent resources that can be consumed by running jobs.

  • Maximum of 48 CPU cores and 4 GPUs for voucher accounts
  • For funded accounts: 144 cores, 12 GPUs

Advanced Vouchers

In order to request resources beyond the basic allowance, we require a discussion meeting on the details of your project.  Advanced vouchers can provide for additional amounts of RCUs or extended terms beyond what a basic voucher offers.

Requesting vouchers for your project

To request your own billable account funded with voucher credits, you must be a KSU faculty member.  Begin by completing the Research Computing Billable Account Request Form.  Once you have your new account ID, you will be able to request services and add users who you want to access those services.

Example: requesting vHPC with voucher credits  

Please note: voucher credits can not be used to fund our REDCap or Secure Enclave services.

Research Computing Core Rates


The rate to use for calculating the cost of using these services is dependent upon the owner of the account.  Rates are increased for academic projects outside of the USG and for other external projects.

Service Unit KSU Rate Other Academic Other External
vHPC CPU 1 core-hour $0.03 $0.04 $0.05
VHPC GPU 1 gpu-hour $0.12 $0.17 $0.22
VHPC Mem GB $0.004 $0.006 $0.007
Ceph Storage 1 TB/Year $28.00 $40.00 $51.00
Consultation Hour $87.00 $125.00 $159.00
Training Hour $58.00 $84.00 $106.00
REDCap Year $5,819.00 unavailable unavailable
Secure Enclave Year *$8,499.00 unavailable unavailable

* Base cost.  The actual secure enclave cost is dependent upon project needs.


vHPC billing

On the first of each month, completed job information is collected from the previous month.  Details about the CPU, GPU and memory resources dedicated to each completed job. With that information, the cost is determined in dollars and Research Computing Units (1 RCU = 1 cpu-hour).

Example: 5 jobs from a KSU-based account 
Job CPUs GPUs Memory Duration
1 1 0 none* 1 hour
2 1 1 16 GB 1 hour
3 4 2 480 GB 1 hour
4 48 4 256 GB 1 hour
5 48 0 360 GB 1 hour

*If not supplied in job script, the default memory is 5 GB per node, regardless of the number of cores requested.

Costs of the 5 Example Jobs:
Job Costs RCUs Notes
1

CPU = 0.03

Mem = 0.02

$0.03 = 1 RCU CPU cost greater than Mem cost
2

CPU = 0.03
GPU = 0.12

Mem = 0.064

$0.15 = 5 RCUs CPU + GPU cost greater than mem cost
3

CPU = 0.12
GPU = 0.24

Mem = 1.92

$1.92 = 64 RCUs Mem cost greater than CPU + GPU cost
4

CPU = 1.44
GPU = 0.48

Mem = 1.02

$1.92 = 64 RCUs CPU + GPU cost greater than Mem cost.
5

CPU = 1.44
GPU = 0.00

Mem = 1.44

$1.92 = 64 RCUs *Even though CPU = Mem, job charged for making 4 GPUs unavailable.

*The billing process takes into account what resources were made unavailable to other users by a job.  So, Job 5 is actually charged for 48 CPU and 4 GPU.

As a quick reference, the rates for KSU users on the vHPC are $0.03 per cpu-hour, $0.12 per gpu-hour and $0.004 per GB-hour. 

Formula = max(GPUs * GPU rate + CPUs * CPU rate, Memory * Memory rate) * time

If you have long running jobs and would like to know the current cost of the job or are interested in optimizing resources for a job, please reach out to tboyle@kennesaw.edu by email or on Teams.