User Tools

Site Tools




The following text describes the charging algorithms for HPC use on ICI-SC hardware

Compute Usage

Supercomputer resources on The Cluster are charged in terms of Resource Units, a common measure of the use of CPU and file storage across all platforms.

The charging formula for RUs consumed by a process is:

RU = Cost × TtCPU

where RU is the charge in Resource Units for the process being considered and TtCPU is the total CPU time in hours for all CPUs.


The formula for calculating total CPU time differs between parallel and serial jobs. Parallel jobs are charged for whole nodes regardless of the ppn request submitted. This means if you were to only request ppn=2 for a 2 node parallel job on Liger, you would be charged as if you requested a ppn=24 regardless.

For serial jobs

 total CPU time = [walltime used] x [ppn requested]

For parallel jobs

 total CPU time = [walltime used] x [max ppn on system] x [nodes requested]

GPU Usage

There is no charge specifically for GPU usage.

File Storage

At this time, there is no charge for file storage.

policies/charging.txt · Last modified: 2016/05/18 14:08 by