Zorbas is a high performance computing cluster (hpc) consisting of 400 cores and 5TB memory in total. There are 5 computing partitions (classes of computers with similar specifications), one login node where users can enter to the system from and an intermediate node where users can test their scripts and/or submit their jobs.
Computing Partitions or Queues
- Bigmem partition can be used for memory intensive jobs. It consists of 1 node with 32 cores and can support processes requiring up to 640GB RAM.
- Hugemem partition can be used for hugely memory intensive jobs. It consists of 1 node with 20 cores and can support jobs requiring up to 1.5TB RAM.
- Batch partition is composed by 10 nodes each one with 20 cores and 128 GB RAM. A user can assign parallel jobs (either in a single node or across several nodes) to the batch partition.
- Fat partition consists of 3 nodes with 40 cores and 500 GB RAM. A user can submit highly cpu intensive jobs to this partition.
- Minibatch partition is composed by 5 nodes each one with 12 cores and 48 GB RAM. A user can assign parallel jobs (either in a single node or across several nodes) to this partition.
For more technical details please refer to the infrastructure page.