Students Immersed in Petascale Computing as Part of Blue Waters Mission

Earthquake preparedness, violent explosions of massive stars at the end of their lives, effectiveness of climate change response policy and teaching students about high-performance computing: These are some of the 130 projects undertaken in the National Center for Supercomputing Applications at the University of Illinois at Urbana-Champaign this year, tapping into the computing power of Blue Waters, the center's high-performance computing system. Among all of the research undertaken, at least one percent of them — 60 million core hours of computational capacity — each year is dedicated to "educational work," projects intended to support the development of a national workforce with expertise in petascale computing.

Blue Waters, the National Science Foundation's most powerful system for sustained computation and data analysis, is a Cray machine with a total peak performance of 13.34 petaflops. The system runs 22,640 XE compute nodes (each containing two AMD Interlagos processors) and 4,228 XK compute nodes (each containing one AMD Interlagos processor and one NVIDIA GK110 "Kepler" accelerator). The configuration allows for extremely large simulations on hundreds of thousands of traditional CPUs for science and engineering projects and development and optimization of applications that leverage the compute power of thousands of GPUs.

The educational work involves more than the use of computational time and storage. Projects can also include in-class, interactive exercises and assignments, workshops, longer "institutes," semester courses and support of internships and fellowships. So far, 200 such projects involving 160 institutions have been performed since the advent of Blue Waters in 2012.

Participants are asked to file a report documenting the impact of the education allocation. Among the comments:

  • "This project introduced many of the students to high performance computing for the first time — setting up batch scripts, requesting interactive nodes, running remote simulations, and using gpu-accelerated programs";
  • "The Blue Waters system gave the students access to a system with much larger scaling capabilities than they typically have access to. In particular, one team was able to scale their code to hundreds of nodes, which would be impossible at their current institutions"; and
  • "The use of Blue Waters enabled students to understand issues of programming at scale (up to 128 nodes [4,096 core equivalents]) and to tune their codes in a dedicated environment where performance is roughly repeatable."

Faculty and students who work on these projects also get the benefit of Blue Waters staff for technical support and as "points of contact" for the projects.

"To date, the NSF Blue Waters Project has provided over 20 billion core-hour equivalents to science, engineering and research projects, supported not just by the NSF, but also by NIH, NASA, DOE, NOAA, and other funders. Without Blue Waters, these funded investigations might not even be possible," said Blue Waters Director and Principal Investigator, Bill Kramer, in prepared statement.

The Blue Waters organization said it accepts education proposals year-round. They're due the first working day of each month, and a response will be given "roughly" about mid-month. The education allocation process is explained on the Blue Waters website.

About the Author

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

Featured

  • artificial intelligence on laptop

    OpenAI to Combine AI Products into Desktop 'Superapp'

    OpenAI is reportedly developing a desktop application that would combine several of its emerging AI products into a single platform, according to reports, marking the latest step in the company's effort to transform ChatGPT from a standalone chatbot into a broader productivity and automation environment.

  • woman surrounded by virtual hologram icons

    Beyond AI Adoption: Designing Learning for an Age of Abundant Intelligence

    Higher education was designed for a world in which access to knowledge, expertise, feedback, mentorship, and authentic learning experiences were inherently scarce. By making many forms of intelligence increasingly abundant, AI is inherently redefining the existing paradigm.

  • digital brain with network connections

    Microsoft Moving to Internally Developed AI Models in Office Apps

    Microsoft is reportedly using its own in-house artificial intelligence models to handle some workloads in Excel and Outlook, offering new evidence that the company is moving its AI strategy beyond model development and into large-scale cost reduction.

  • Profile silhouette of a person thoughtfully touching their chin, overlaid with transparent data visualizations and digital interface elements suggesting artificial intelligence and analytics.

    The Institutional Knowledge Shift Is Reshaping Higher Ed IT

    Higher education IT leaders are navigating a quiet but consequential transition: Experienced team members are retiring or leaving for private-sector roles, and the teams replacing them are smaller, newer, and often stretched thin. The result is a structural shift in how technology decisions are made, executed, and sustained.