UC San Diego Deploying 2 PFLOPS System Supporting High-Performance Virtualization

Two universities are working on high performance research clusters based on Dell hardware. Both are expected to go online in 2015. The San Diego Supercomputer Center at the University of California, San Diego is deploying Comet, a virtualized petascale supercomputer to address general research areas such as social sciences and genomics. Comet is funded by a $6 million National Science Foundation (NSF) grant. The Texas Advanced Computing Center (TACC) at the University of Texas at Austin is building Wrangler, a data analysis and management system funded by a $6 million NSF grant for the national open science community.

Comet is expected to have peak performance of "nearly" 2 petaFLOPS; however, its design is intended to support many modest-scale jobs. Each node will be equipped with two processors, 128 GB of traditional DRAM and 320 GB of flash memory. Comet will also include large-scale nodes and graphics processing unit-heavy nodes for work with intensive visualization aspects.

Comet will be the first Extreme Science and Engineering Discovery Environment (XSEDE) production system to support high-performance virtualization. XSEDE is a five-year, multi-institutional, NSF-funded project that will let researchers share computing resources, data, and support on a single virtual system.

"Comet is all about [high performance computing] for the 99 percent," said San Diego's Supercomputer Center Director Michael Norman. "As the world's first virtualized HPC cluster, Comet is designed to deliver a significantly increased level of computing capacity and customizability to support data-enabled science and engineering at the campus, regional and national levels."

U Texas' Wrangler will feature Dell PowerEdge R620 and R720 rack server compute nodes and 20 petabytes of storage built with PowerEdge C8000 components. It's expected to integrate with TACC's Stampede supercomputer and through that to XSEDE.

"Wrangler is designed from the ground up for emerging and existing applications in data intensive science," said Dan Stanzione, Wrangler's lead principal investigator and TACC deputy director. "Wrangler will be one of the largest secure, replicated storage options for the national open science community."

In January 2014, the university also expects to deploy Maverick, which will perform remote data analysis and visualization work; Maverick will use HP and Nvidia components.

Dell introduced both institutions as customers during SC13, an international conference for high-performance computing taking place this week in Denver.

About the Author

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

Featured

  • digital brain integrating legal regulation and security interface

    Agentic AI Moves from Pilot Phase to Production, Bringing Governance to the Forefront

    New research from Caylent, an AI-focused Amazon Web Services Premier Tier Services Partner, found that enterprises are already moving agentic AI beyond pilots and into production environments. At the same time, organizations are putting strict conditions around autonomy, making governance and control the next major challenge for enterprise AI adoption.

  • abstract electronic circuit board 3d rendering

    Report: Content Infrastructure, Governance Lag Behind Agentic AI Adoption

    AI agents have quickly moved into mainstream enterprise use, but the content infrastructure needed to support them has struggled to keep up, according to a new report from cloud content management company Box.

  • circuit patterns

    Anthropic Launches Lower-Cost Claude Sonnet 5

    Anthropic has released Claude Sonnet 5, positioning the model as its most autonomous mid-tier offering to date and a lower-cost alternative to its flagship Opus 4.8 system. The company said the model can plan multi-step tasks, operate tools such as browsers and terminals, and complete agentic work at a level that previously required larger and more expensive models.

  • abstract glowing ai chip on circuit board

    Gartner Marks Enterprise Move from AI Experiments to AI Engineering

    According to Gartner's recent "Hype Cycle for Enterprise Architecture, 2026" report, enterprises are moving from AI experimentation toward a more industrialized approach to AI delivery.