This page is a detailed explanation on the method for calculating resource usage costs on the HURCS cluster named Moriah.
Chargeable compute resources are:
Storage
CPU cores
Memory
GPU
Charging is done in the beginning of each month, for the cluster usage on the previous month, by deducting the costs from the credits each PI has in the HURCS account.
Cluster usage costs are calculated based on storage and compute resource type. Please read the following descriptions carefully and make sure you understand your cost structure.
The cost for storage usage is for disk quota, NOT the actual usage of storage. Disk quotas can only be in increments of 1 TB (that is, quota cannot be for example 3.5TB).
We provide two kinds of disk storage: Fast and Archive. Fast storage should be used for files that are currently in use. Archive storage is cheaper and may be used to store data that is not accessed often, such as old research results, etc. On top of the storage service itself, we provide two kinds of backup services: snapshots and full backup. The different storage and backup options are implemented by dividing the storage into several volumes, and accordingly, charging is done for the quota allocated in each volume, as described in the following table:
| Volume | Details | Path | Total cost (for 1TB/1Month) |
| Fast, no snapshots | Fast storage for temporary files (without any backup options) | /sci/nosnap/<PI login> | $4 for 1TB |
| Fast, with snapshots | Main working storage for computation work | /sci/labs/<PI login> | $5 for 1TB |
| Fast with full backup | Fast storage for a full backup service | /sci/backup/<PI login> | $5 for 1TB + $2.5 per TB for backup service (total, $7.5) |
| Archive | Long term storage. Cannot be used for computation | /sci/archive/<PI login> | $2 for 1TB |
| Archive with backup | Archive storage + full backup | /sci/backup/Archive/<PI login> | $2 for 1TB + $2.5 per TB for backup service (total, $4.5) |
Each lab is assigned 1TB of fast (with snapshots) storage by default. PI’s who don’t need any lab storage can ask for this storage option to be revoked, and will not be charged for it.
Requests for changes in quota allocations can be done by filling this form.
Fast (with snapshots) = 10TB
Archive = 30TB
Backup = 5TB
Monthly cost = 10*5 + 30*2 + 5*7.5 = $147.5
See here for more details about the storage folders structure in HURCS.
Jobs submitted to the cluster are billed based on the amount of resources allocated, not just what was requested or used. To simplify billing, we define a unified cost metric: the CRU (Compute Resource Unit).
1 CRU = 1 hour of full usage of a single compute node
Jobs are charged according to how much of a node’s resources they used, relative to the node's full capacity.
| Node Category | Node Name(s) | GPU Type | CRU Cost |
|---|---|---|---|
| CPU-only | glacier |
– | $1.024 |
| GPU (L4) | catfish |
L4 (24 GB) | $0.80 |
| GPU (L40s) | salmon |
L40s (48 GB) | $1.60 |
| GPU (H200) | goldfish |
H200 (141 GB) | $4.00 |
| GPU (A100 80GB) | dogfish |
A100 (80 GB) | $3.20 |
Determine the percentage of CPU, Memory, and GPU memory used:
CPU usage % = CPUs used / total CPUs per node
Memory usage % = RAM used / total RAM per node
GPU usage % = GPU memory used / total GPU memory per node
CRU value = maximum of the three usage percentages
Job Cost = CRU value × duration (in hours) × node CRU cost
🔒 Note: Jobs cannot span multiple node types (e.g., glacier + dogfish)
Job: 1 CPU, 6 GB RAM
Node: glacier → 128 CPUs, 1024 GB RAM
Usage:
CPU: 1 / 128 = 0.0078
Memory: 6 / 1024 = 0.0059
→ CRU = 0.0078
Time: 2 hours
Cost = 0.0078 × 2 × $1.024 = $0.016
Job: 1 A100 (80 GB), 1 CPU, 32 GB RAM
Node: dogfish → 8×A100 (640 GB total), 256 CPUs, 2 TB RAM
Usage:
GPU: 80 / 640 = 0.125
CPU: 1 / 256 = 0.0039
Memory: 32 / 2048 = 0.0156
→ CRU = 0.125
Time: 10 hours
Cost = 0.125 × 10 × $3.20 = $4.00
Job: 1 L4 (24 GB), 2 CPUs, 64 GB RAM
Node: catfish → 8×L4 (192 GB total), 64 CPUs, 1 TB RAM
Usage:
GPU: 24 / 192 = 0.125
CPU: 2 / 64 = 0.0313
Memory: 64 / 1024 = 0.0625
→ CRU = 0.125
Time: 6 hours
Cost = 0.125 × 6 × $0.80 = $0.60
Job: 1 L40 (48 GB), 2 CPUs, 128 GB RAM
Node: salmon → 8×L40s (384 GB total), 64 CPUs, 1.5 TB RAM
Usage:
GPU: 48 / 384 = 0.125
CPU: 2 / 64 = 0.0313
Memory: 128 / 1536 = 0.0833
→ CRU = 0.125
Time: 4 hours
Cost = 0.125 × 4 × $1.60 = $0.80
Job: 1 H200 (141 GB), 4 CPUs, 128 GB RAM
Node: goldfish → 8×H200 (1128 GB total), 128 CPUs, 1.8 TB RAM
Usage:
GPU: 141 / 1128 = 0.125
CPU: 4 / 128 = 0.0313
Memory: 128 / 1843 = ~0.0695
→ CRU = 0.125
Time: 5 hours
Cost = 0.125 × 5 × $4.00 = $2.50