Rhea Cluster

Rhea is a (521)-node commodity-type Linux® cluster. Rhea provides a conduit for large-scale scientific discovery via pre- and post-processing of simulation data generated on Titan. Each of Rhea’s first 512 nodes contain two 8-core 2.0 GHz Intel Xeon processors with Intel’s Hyper-Threading (HT) Technology and 128GB of main memory. Rhea also has nine large memory GPU nodes. These nodes each have 1TB of main memory and two NVIDIA K80 GPUs with two 14-core 2.30 GHz Intel Xeon processors with HT Technology. Rhea is connected to the OLCF’s high performance Lustre® filesystem, Atlas.

Specifications and Features

  • Architecture: Commodity-type Linux® cluster
  • Processors:
    • – default partition: dual 8-core Intel® Xeon® E5-2650 @ 2.0 GHz
    • – gpu partition: dual 14-core Intel® Xeon® E5-2695 @ 2.3 GHz
  • Nodes: 521
  • Cores/node:
    • – default partition: 16
    • – gpu partition: 28
  • Total cores: 8,444
  • Memory/node:
    • – default partition: 128GB
    • – gpu partition: 1TB
  • Memory/core:
    • – default partition: 8GB
    • – gpu partition: 36.5GB
  • Interconnect: 4X FDR Infiniband, 56GB/s max
  • GPUs: NVIDIA® K80

System Support

The System User Guide is the definitive source of information about Rhea, and details everything from connecting to running complex workflows. Please direct questions about Rhea and its usage to the OLCF User Assistance Center by emailing help@olcf.ornl.gov.

Latest Rhea Articles