NREL Acquires Next-Generation High Performance Computing System

Kestrel Will Take Flight and Bring the United States Closer to a Clean Energy Future

Dec. 1, 2021 | Contact media relations

The American Kestrel soaring through the air.
The new supercomputer's namesake—the American Kestrel—hunting for prey. Photo from iStock

The National Renewable Energy Laboratory (NREL) has selected Hewlett Packard Enterprise (HPE) to build its third-generation, high performance computing (HPC) system, called Kestrel.

Named for a falcon with keen eyesight and intelligence, Kestrel’s moniker is apropos for its mission—to rapidly advance the U.S. Department of Energy’s (DOE’s) energy research and development (R&D) efforts to deliver transformative energy solutions to the entire United States.

Installation of the new system will begin in the fall of 2022 in NREL’s Energy Systems Integration Facility (ESIF) data center. Kestrel will complement the laboratory’s current supercomputer, Eagle, during the transition. When completed—in early 2023—Kestrel will accelerate energy efficiency and renewable energy research at a pace and scale more than five times greater than Eagle, with approximately 44 petaflops of computing power.

Eagle enables R&D breakthroughs across multiple programs within DOE’s Office of Energy Efficiency and Renewable Energy (EERE); these breakthroughs are a promising preview of achievable advancements with the highly anticipated Kestrel.

As the dedicated HPC system for EERE, 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 future energy systems. Rapidly advancing applications and technologies in artificial intelligence (AI) and machine learning are fostering innovation and expansion of research into new directions for computing. These workflows drive complementary physics and data-driven approaches by fusing simulation with new sensor data sources. Kestrel’s heterogeneous architecture—which includes both CPU-only and GPU-accelerated nodes—is designed to enable these emerging workflows, providing EERE and industry partners with the ability to tackle the energy challenges for moving into a renewable and sustainable future.

Years of collaborative work in the HPC domain mean that NREL and HPE are poised to successfully execute the Kestrel deployment beginning in the fall of 2022.

HPE will build Kestrel using the HPE Cray EX supercomputer with design capabilities that are fully compatible with the warm-water waste heat recovery system currently used in NREL’s ESIF data center.

Kestrel will be composed of a balanced capability of future next generation Intel® Xeon® Scalable processors (code-named “Sapphire Rapids”) and NVIDIA A100NEXT Tensor Core GPUs to accelerate AI. The system will also feature HPE Slingshot, an Ethernet fabric to address higher speed and congestion control for larger data-intensive and AI workloads. With high-speed connectivity connecting more than 75 petabytes of parallel file system storage using the Cray ClusterStor E1000 from HPE, users will be empowered to tackle complex, data-centric workflows and immerse themselves in interactive data analytic visualizations.

With the Kestrel HPC system on the horizon, NREL remains poised to continue delivering critical energy efficiency and renewable energy advancements with its HPC-supported capabilities.

Tags: Computational Science,Partnerships