Crypto Currency News
Ethereum Classic

Argonne Adds GPUs to Theta Supercomputers to Accelerate Coronavirus Research

ALCF employees add NVIDIA DGX A100 nodes to Theta. (Image: Argonne National Laboratory)

A 15 terabyte solid state drive provides a bandwidth of up to 25 gigabits per second for each node. The computing connection consists of 24 Mellanox QM9700 HDR200 40-port switches, which are wired in a non-blocking fat tree topology.

“This upgrade significantly increases Theta’s computing power,” said Mark Fahey, director of operations at ALCF. “The capabilities it contains will accelerate the complex and diverse workloads that define contemporary scientific computing and integrate data analysis with AI training and learning into a single platform.”

The DGX A100 nodes are integrated in Theta using the ALCF’s Cobalt HPC scheduler. Initial planning is available at the node level, with custom planning at the GPU level being done in the near future.

“While this additional hardware is intended to enable important research in itself, it is a stepping stone to utilize the advanced GPU-accelerated systems that will be available in the near future – that is, Polaris and Aurora,” said Katherine Riley, ALCF director of science .

Like the Theta upgrade, Polaris, the ALCF’s next machine, has a heterogeneous architecture that uses both CPUs and GPUs. Since many of its functions are derived from the GPU, Polaris will be a scalable bridge preparing ALCF users for the Aurora Exascale machine.

The enhanced theta hardware was entirely dedicated to coronavirus research when it was deployed in May. While coronavirus research remains the system’s top priority, Argonne is expanding availability to the wider user community.

“The difference in computing power accelerated our work almost instantly,” said Arvind Ramanathan, a computational biologist at Argonne who leads a group of researchers aimed at unraveling the basic biological mechanisms of the virus while also finding potential therapeutics for treating the disease to identify. “Our data-intensive workloads, which combine AI, machine learning techniques, and molecular dynamics simulations, require significant brute force to keep the pace of discovery at a decent pace.”

With the imminent arrival of Polaris and Aurora – and the exascale era with the latter – that pace will continue to accelerate.

The Argonne Leadership Computing Facility provides supercomputing capabilities to the scientific and engineering community to advance fundamental discovery and understanding across a wide range of disciplines. The ALCF is supported by the US Department of Energy’s (DOE) Advanced Scientific Computing Research (ASCR) program and is one of two DOE leadership computing institutions in the nation dedicated to open science.

Argonne National Laboratory seeks solutions to pressing national problems in science and technology. Argonne is the country’s first national laboratory and conducts cutting-edge and applied scientific research in almost all scientific disciplines. Argonne Researchers work closely with researchers from hundreds of corporations, universities, and federal, state and local agencies to help them solve their specific problems, advance America’s scientific leadership, and prepare the nation for a brighter future. With employees from more than 60 nations, Argonne is administered by UChicago Argonne, LLC for the US Department of Energy’s Office of Science.

The Department of Energy at the Department of Energy is the biggest proponent of basic science in the United States, working to address some of the most pressing challenges of our time. Further information can be found at https: // ener gy .gov / science.

Source: NILS HEINONEN, Argonne

Comments are closed.