National systems: Difference between revisions

From Alliance Doc
Jump to navigation Jump to search
(updated Cedar core count (for CPUs))
(updated Graham core count (CPU))
Line 38: Line 38:
* GPU and big memory nodes
* GPU and big memory nodes
* Small cloud partition
* Small cloud partition
|| 33,376 cores || In production
|| 41,548 cores || In production
|-
|-
| [[Niagara|Niagara]] ||
| [[Niagara|Niagara]] ||

Revision as of 18:59, 6 April 2020

Other languages:


Compute[edit]

Overview[edit]

Cedar, Graham and Béluga are similar systems with some differences in interconnect and the number of large memory, small memory and GPU nodes.

Name Description Capacity Status
CC-Cloud Resources

Arbutus
East.cloud

OpenStack IAAS Cloud 7,640 cores In production
(integrates former west.cloud)
Béluga

heterogeneous, general-purpose cluster

  • Serial and small parallel jobs
  • GPU and big memory nodes
34,880 cores In production
Cedar

heterogeneous, general-purpose cluster

  • Serial and small parallel jobs
  • GPU and big memory nodes
  • Small cloud partition
94,528 cores In production
Graham

heterogeneous, general-purpose cluster

  • Serial and small parallel jobs
  • GPU and big memory nodes
  • Small cloud partition
41,548 cores In production
Niagara

homogeneous, large parallel cluster

  • Designed for large parallel jobs > 1000 cores
60,000 cores In production

All systems have large, high-performance attached storage. See National Data Cyberinfrastructure for an overview; follow the links above for individual system for details.

CCDB descriptions[edit]

General descriptions are also available on CCDB: