Tariffs: Difference between revisions

From HPCwiki
Jump to navigation Jump to search
No edit summary
No edit summary
 
(2 intermediate revisions by the same user not shown)
Line 12: Line 12:
|€ 0.0195
|€ 0.0195
|€ 0.00143
|€ 0.00143
|-
|Low priority queue
|€ 0.0150
|€ 0.0011
|}
|}


Line 22: Line 18:
!Tariff per device per hour (gpu/hour)
!Tariff per device per hour (gpu/hour)
|-
|-
|€ 0.585
|€ 0.45
|}
|}


Line 45: Line 41:
!Tariff per node per day (node/day)
!Tariff per node per day (node/day)
|-
|-
|€ 30
|€ 50
|}
|}



Latest revision as of 13:43, 7 February 2025

Computing: Calculations (cores)

Queue CPU core hour GB memory hour
Standard queue € 0.0150 € 0.0011
High priority queue € 0.0195 € 0.00143

Computing: GPU Use

Tariff per device per hour (gpu/hour)
€ 0.45

Storage

Tariffs per year per TB

Lustre Backup Lustre Nobackup Lustre Scratch Home-dir Archive
€ 150 € 100 € 100 € 150 € 125

Reservations

Tariff per node per day (node/day)
€ 50

Notes

If you are a member of a group with a commitment, then these costs get deducted from that commitment. Once you get to around 125% of your commitment we will take action to fix things.

Example

You are running a job that needs 4 cores, 32G of RAM and runs for 90 minutes in the std quality. To run this, you over-request resources slightly, and submit a job that requests 4 CPUs, 40G of RAM and with a time limit of 3 hours. Your job is done after two hours, using at maximum 3 CPUs and 32G of RAM.

Thus, your costs are:

4 * 0.015 * 2 = 0.12 EUR for the CPU

40 * 0.0011 * 2 = 0.088 EUR for the memory

Total: € 0.208

So you are billed for the duration that you claimed the 4CPUs and 40G of RAM, not the 3 CPUs and 32G RAM you actually used.