National systems

Revision as of 20:37, 23 March 2022 by Plstonge (talk | contribs) (Added Hpss)


Outdated

This page or section contains obsolete information and some statements may not be valid. The technical documentation is currently being updated by our support team.



Other languages:

Compute clusters

All general-purpose systems are similar with some differences in interconnect and the number of small memory, large memory and GPU nodes. Niagara is a different system and is designed for large parallel jobs.

All systems have large, high-performance attached storage; see the relevant cluster page for more details.

Types of compute clusters

Type Type of nodes Type of jobs
General-purpose
  • Small memory nodes
  • Regular nodes (4GB/core)
  • Large memory nodes
  • GPU nodes
  • Serial and small parallel jobs
  • Small or large memory jobs
  • GPU jobs
Large parallel
  • Uniform nodes (4GB/core)
  • Optimized interconnect
  • Parallel jobs requiring +1000 cores

List of compute clusters

Name and link Type CCDB Descriptions Status
Béluga General-purpose In production
Cedar General-purpose In production
Graham General-purpose In production
Narval General-purpose In production
Niagara Large parallel In production

Cloud - Infrastructure as a Service

Our cloud systems are offering an Infrastructure as a Service (IaaS) where OpenStack is the main user interface.

Name Description Status
Arbutus Cloud
  • Compute intensive and persistent workloads
  • vGPU nodes
In production
Béluga Cloud
  • Compute intensive and persistent workloads
In production
Cedar Cloud
  • Compute intensive and persistent workloads
In production
Graham Cloud
  • Compute intensive and persistent workloads
In production