Computational Neuroscience Compute Cluster
The computational brain sciences group manages a compute cluster with 500TB storage capacity and high-performance compute nodes. The cluster is supported by two CFI awards (Diedrichsen / Khan) and the computational and human core of the BrainsCAN initiative.
How does the cluster work?
Research groups can have one or more multiple disk shares (i.e. storage volumes), which can be accessed by mounting them to local machines, or accessed through other file transfer protocols. Users can also login to the system to access a virtual Linux desktop computer, which runs on cores that are directly connected to these storage volumes. Standard users can access 4-core machines, high-performance users (extra charge, see below) can access virtual machines with up to 12 cores, 32GB of RAM, and GPUs.
How do I get access to the cluster?
The PI of the group first needs to submit an for the group and provide a speed code for the access charge. Users within these labs can then can apply individually.
Click here for more information on cluster access.
What does access to the cluster cost?
Fees are charged on an annual basis. For the purpose of full cost recovery the annual fees are set to:
- $150/TB* for storage
- Standard user accounts are free
- $3000* for the first high-performance user in the group
- $1500* for each following high-performance user in the group
*Note that due to the current CFI and BrainsCAN support, we only charge ⅓ of these nominal prices. The fees will be used for upgrades and extensions of the storage and compute system. We reserve the right to adjust the fee structure on a yearly basis depending on usage.
