HOUSTON — The U.S. Department of Energy’s National Renewable Energy Laboratory (NREL) is engaging Hewlett Packard Enterprise (HPE) to build a supercomputer to support ongoing research and development.
R&D supported by the supercomputer will transform energy from geothermal, water, wind, solar, and fuels, according to HPE this month.
The supercomputer will also support energy initiatives related to security, resilience, storage, systems integration, energy justice, and community transitions as well as transportation and mobility, buildings, and advanced manufacturing.
In continuing its naming theme of supercomputers that honors various bird species, such as with previous system generations named Peregrine and Eagle, NREL has named the new supercomputer Kestrel, after the American falcon.
Once completed in 2023, the supercomputer will have more than five times greater performance than NREL’s existing system, Eagle, with about 44 petaflops of peak performance. It will be hosted in NREL’s Energy Systems Integration Facility (ESIF) data center in Golden, Colorado.
HPE will build Kestrel using the HPE Cray EX supercomputer, a next-generation high performance computing (HPC) platform that provides end-to-end HPC solutions to scale performance and harness insights more efficiently through advanced modeling, simulation, artificial intelligence (AI) and analytics capabilities.
Kestrel will play a critical role in computing across the research portfolio, advancing research in computational materials, continuum mechanics, and large-scale simulation and planning for energy systems.
The HPE Cray EX also features liquid-cooling capabilities that support NREL’s showcase facility for demonstrating data center efficiency, which has achieved a world-leading annualized average power usage effectiveness (PUE) rating of 1.036.
HPE will feature next-generation Intel Xeon Scalable processors, NVIDIA A100NEXT Tensor Core GPUs to accelerate AI, and HPE Slingshot, an Ethernet fabric built for next-generation supercomputing to address higher speed and congestion control for larger data-intensive and AI workloads.
Additionally, NREL’s Kestrel will deliver more than 75 petabytes of parallel file system storage using the HPE Cray Clusterstor E1000 storage system for expanded storage and intelligent tiering capabilities to tackle complex, data-intensive workflows.
“NREL is excited to officially announce the procurement of our new supercomputer,” said Kris Munch, lab program manager of advanced computing at NREL. “Kestrel will help EERE researchers and industry partners tackle today’s toughest energy challenges and bring the United States one step closer to a clean energy future.”
Bill Mannel, VP and GM of HPC at HPE, said the company has a long-standing collaboration with NREL.
“We look forward to continuing our relationship with NREL and are honored to have been selected to deliver an advanced supercomputer with Kestrel that will significantly augment the laboratory’s efforts in making breakthrough discoveries of new, affordable energy sources to prepare for a sustainable future,” Mannel said.