16 Departments
58 Research Groups
53 Projects
129 Publications
18 Advanced Degrees
327,519 Completed Simulations
50,461,576 CPU Core Hours

Named after the greatest of the Great Lakes and built with Rocks Cluster Distribution 6.1.1 (with CentOS 6.3), Superior is a shared high-performance computing cluster.

It is used for a wide variety of research projects, and provides 32 TFLOPS of CPU and 13 TFLOPS of GPU computing capacity. A schematic representation of Superior's layout is available here.

Superior has one front end, two login nodes, one 48 TB RAID60 NAS node serving the /research/ partition, 72 traditional CPU compute nodes [each having 16 CPU cores (Intel Sandy Bridge E5-2670 2.60 GHz) and 64 GB RAM] and 5 GPU compute nodes [each having 16 CPU cores (Intel Sandy Bridge E5-2670 2.60 GHz), 64 GB RAM and 4 NVIDIA Tesla M2090 GPUs] for use by all researchers.

A Gigabit ethernet backend network serves the administrative needs of this cluster, and a 56 Gbps InfiniBand network serves its computing needs.

Rocks Cluster Distribution Originally started by National Partnership for Advanced Computing Infrastructure and San Diego Supercomputer Center and called NPACI Rocks, Rocks Cluster Distribution is aimed at making every aspect (deploy, manage, upgrade and scale) of high performance computing clusters easy.

National Science Foundation Rocks is supported by the National Science Foundation, under grants OCI-0721623 and OCI-1032778.

Featured researcher and project(s)

Dr. Laura Brown
Associate Professor, CS

Dr. Brown's research is centered broadly on the application and design of methods in artificial intelligence ... [Read more]

Dr. Lyon (Brad) King
Professor, ME-EM

Dr. King's research is focused on electric powered spacecraft propulsion. Electric propulsion uses ... [Read more]

  1. Open ServiceDesk Plus Portal
  2. Log in with ISO credentials
  3. Use a brief but descriptive ISSUE TITLE in the Subject field

Including as much information as possible (for e.g., command sequence/work flow that is causing the issue, job ID, full path to the folder where the simulation was started from, as is error messages, screenshots, etc.) will help diagnose and resolve the issue in a timely manner.

Lab-grown diamonds https://t.co/mZe6Q6ZCqO @ORNL

Predicting PTSD after trauma https://t.co/iRhjIDTmQJ

Extreme scale earthquake simulations https://t.co/52b1ZJhwwc @NVIDIA