Skip to main content
Add as a preferred source on Google


U Pittsburgh Ups Research Capacity with Linux Cluster Named Frank

  • By Dian Schaffhauser
  • 07/20/11

The University of Pittsburgh has expanded its high performance computing resources used by researchers across campus. The Pennsylvania institution's Center for Simulation and Modeling (SAM) has added a heterogeneous Linux cluster designed and built by Penguin Computing.

Penguin, a San Francisco-based firm, integrates components from multiple companies. In this installation, the cluster, named "Frank," has 40 nodes. Three quarters of those have two six-core Xeon "Westmere" processors from Intel with 48 GB of memory; the remaining nodes have four 12-core Opteron "Magny-Cours" processors from AMD with 128 GB of memory; four of the Westmere nodes also include Nvidia Fermi graphics processing units to speed up specific types of applications.

Most of the nodes are connected with quad data rate InfiniBand for data communications. The new cluster runs Penguin's Scyld ClusterWare and TaskMaster software, which is already being used to manage resources on other Penguin clusters at the university.

Administration for the newest cluster will be a joint effort between SAM and the university's IT division, Computing Services and Systems Development.

"When our research efforts called for a new cluster, there was no question that we would go to Penguin for support," said Kenneth Jordan, a professor in U Pittsburgh's School of Arts & Sciences. "We have purchased several computer clusters from Penguin and have been very pleased with their reliability. There is a major advantage in terms of maintaining the various clusters to use the same operating system and management and queue software on all systems."

About the Author

Dian Schaffhauser is a former senior contributing editor for 1105 Media's education publications THE Journal, Campus Technology and Spaces4Learning.

Featured

  • businesspeople in silhouette with colorful network lines

    Report: AI Will Reshape Work More than Replace It, but Global Impact Is Uneven

    Richer countries face greater exposure to AI-driven changes than developing countries, which are less exposed to AI but risk being left behind, according to a joint report from the International Labour Organization and World Bank.

  • abstract coding

    Anthropic's New AI Model Targets Coding, Enterprise Work

    Anthropic has released Claude Opus 4.6, introducing a million-token context window and automated agent coordination features as the AI company seeks to expand beyond software development into broader enterprise applications.

  • stylized illustration of people conversing on headsets

    AI and Our Next Conversations in Higher Education

    Ryan Lufkin, the vice president of global strategy for Instructure, examines how the focus on AI in education will move from experimentation to accountability.

  • Abstract digital cloudscape of glowing interconnected clouds and radiant lines

    Cloud Complexity Outpacing Human Defenses, Report Warns

    According to the 2026 Cloud Security Report from Fortinet, while cloud security budgets are rising, 66% of organizations lack confidence in real-time threat detection across increasingly complex multi-cloud environments, with identity risks, tool sprawl, and fragmented visibility creating persistent operational gaps despite significant investment increases.