Resources

Xanadu High-Performance Compute Clusters

Over 10,000 CPU Cores with 65 TB of RAM capable of processing at 300 TFLOPs and comprised of the following hardware:

  • 10 Dell R730 nodes with two, 18-core Intel Xeon E5-2697v4 processors, 256 GB RAM and 10 gigabit interfaces
  • 5 Dell nodes with two, 10-core Intel Xeon E5-2660v2 processors, 256 GB RAM and 10 gigabit interfaces
  • 1 Dell R730 node with two, 18-core AMD Opteron processors, 256 GB RAM and 10 gigabit interfaces
  • 1 Dell node with two, 24-core  AMD EPYC processors, 264 GB RAM and 10 gigabit interfaces
  • 19 Dell C6145 nodes with four, 12-core AMD Opteron processors, 256 GB RAM and 10 gigabit interfaces
  • 15 Dell C6145 nodes with four 8-core AMD Opteron processors and 256 GB RAM and 10 gigabit interfaces
  • 24 Penguin nodes with Intel Xeon Gold 6230 processors, 192 GB RAM ad 10 gigabit interfaces
  • 3008 NVIDIA Tesla M2075 GPU cores
  • Job Management provided by Slurm Workload Manager and provisioning provided by Bright

 

Virtualization Infrastructure

  • 17 Dell PowerEdge hosts with 952 CPU cores and 8.7 TB RAM running VMWare 7 hosting 300+ Windows and Linux virtual machines with SSD high OPS performance cache tier

 

Datacenter Infrastructure

  • UPS generator backed power with redundant cooling
  • 3×40 Gbe dark fiber connection to off-site DR location

 

Network (100+ Gbe)

  • Full non-oversubscribed 10/40/100 GbE datacenter network core layer
  • BioScienceCT Research Network – 100 GbE to CEN, Internet2, Storrs
  • HPC Science DMZ – low latency, 80 Gb-capable firewall

 

Storage

  • 14 PB of storage including 775 TB Quantum, 2.2 PB EMC Isilon, 2.6 PB Qumulo QC208, 1.5 PB Qumulo K168-T scale-out clusters along with 3.8 PB Amplidata, and 3.0 PB Scality Geo-Spread cloud storage

 

Computational Biology Core

  • CBC provides computational power and technical support to UConn researchers and affiliates.
  • Please visit the CBC website for more information: Computational Biology Core.
  • Join the official CBC Slack channel for up to date news and to request help: UCONN-CBC.slack.com.