GPU Boost: $5M NSF Enhancement for PSC’s Bridges-2 HPC

A $4.9-million award from the National Science Foundation has funded an upgrade to the Pittsburgh Supercomputing Center’s flagship Bridges-2 supercomputer. The grant allows the center to add late-model Nvidia H100 graphics processing units to the system for research in and requiring artificial intelligence.

PSC said the NSF award will add a pod of 10 HPE Cray 670 nodes with eight H100-SXM5-80GB GPUs and 2 TB node memory each, interconnected by Infiniband. It will also enhance the data capacity and I/O performance of the Bridges-2 three-tiered file system to support the expected increase in ML and data-intensive workflows.

NSF initially awarded $10 million to PSC to build Bridges-2, which began production operations in 2021. In addition to massive Big Data and traditional HPC problems, the system was designed to address development and application of AI methods, including machine learning, to a range of scientific challenges.

“Bridges-2 is very popular with the scientific community,” said Barr von Oehsen, PhD, Director of PSC. “This expansion improves this already positive experience by offering more options for AI workloads. We can’t wait to see the science impact these new servers will enable.”

The performance increase will support research in fields such as:

“Bridges-2 has already enabled many impactful ML projects and projects involving ML and HPC using the existing V100-based GPU nodes,” said Sergiu Sanielevici, PhD, Director of Support for Scientific Applications at PSC and Principal Investigator in the Bridges-2 project. “Augmenting this capability with H100-based GPU nodes will significantly improve the performance of our community’s ML and HPC workloads.”