The world’s largest academic supercomputer has a busy year ahead, giving researchers from 45 institutions in 22 countries time for its upcoming operation.
Frontera, which is based at the University of Texas at Austin’s Texas Advanced Computing Center (TACC), said it allocated time for 58 experiments through its Large Resource Allocation Committee (LRAC), which handles the largest proposals. To qualify for LRAC funding, proposals must justify the effective use of at least 250,000 node hours and demonstrate that they would otherwise be unable to complete the research.
Two additional grant types are also available for smaller projects, but LRAC projects utilize the majority of Frontera nodes: an estimated 83% of Frontera’s workload in 2022-23 will be LRAC projects.
Frontera was built in 2019 and premiered at the top 500 fifth place in the supercomputer list. Since then, the CPU-based, 8.008-node Supercomputer has slipped to 13th place, but TACC still claims it’s “the most powerful supercomputer in science.”
In addition to its 38.7 pFLOP main system, Frontera also includes the Longhorn GPU-accelerated workload systems, the Frontera GPU system consisting of 90 immersion-cooled Nvidia GPU nodes, and its Ranch tape storage system.
Getting TACC back on track
2020 was a bad year for the world and a particularly busy one for Frontera and TACC, which was immediately redirected to COVID-19 research, which TACC Director Dan Stanzione described as a “great effort for us.”
“Ten million node hours and approximately 50-70 million core hours went into COVID-19,” Stanzione called. TACC and Frontera worked in the areas of molecular dynamics, drug discovery, epidemiology and genomics related to the coronavirus.
LRAC experiments are among the largest and most complicated tasks Frontera can undertake and the list of experiments planned for the coming year reflects this.
For example, researchers at Carnegie Mellon University and the University of California Riverside plan to use Frontera to develop super-resolution simulations of galaxies and quasars, which the team say are necessary to keep up with advances in telescope technology. In particular, the team wants to find a way to overcome simulation limitations that force researchers to maximize resolution or volume, but not both.
Another experiment hopes to collect data on simulated flows at Mach 6 speeds against a surface at a 35-degree angle. This experiment aims to improve understanding of vehicles moving at supersonic speeds.
Advances in supercomputing are also being tested, with researchers at Binghamton University in New York planning to use Frontera to screen a large body of potential chemicals for use as superconductors, a la drug discovery.
Many of the remaining experiments [PDF] deal with astrophysical modelling, while others deal with supercell thunderstorms, elevation modeling and quantum computing. ®