Mirror Review
June 6th, 2025
Summary:
- The U.S. Department of Energy (DOE) has announced a new, groundbreaking US supercomputer Doudna, named after Nobel laureate and CRISPR pioneer Jennifer Doudna, a Berkeley Lab-based biochemist.
- This new flagship supercomputer, also known as NERSC-10, is set to launch in 2026 at Lawrence Berkeley National Laboratory (Berkeley Lab).
- This powerful machine is a collaboration between Dell Technologies and NVIDIA.
- It’s designed to significantly accelerate scientific discovery across various fields by merging artificial intelligence (AI) with traditional simulation and data analysis.
National Goals and Inspirations for the US Supercomputer Doudna
The supercomputer Doudna represents a significant national investment aimed at maintaining U.S. leadership in high-performance computing.
U.S. Energy Secretary Chris Wright highlighted its importance, stating, “It will advance scientific discovery from chemistry to physics to biology and all powered by — unleashing this power — of artificial intelligence”.
He further emphasized, “AI is the Manhattan Project of our time, and Doudna will help ensure America’s scientists have the tools they need to win the global race for AI dominance”.
Jennifer Doudna expressed her surprise and delight at having a supercomputer named after her, adding, “I think we’re standing at a really interesting moment in biology”.
Technical Specifications of The Dell and NVIDIA Partnership Powering Doudna
Doudna will be built by Dell Technologies, utilizing their advanced ORv3 direct liquid-cooled server technology and PowerEdge servers.
It will be powered by NVIDIA’s next-generation Vera Rubin platform, which includes both high-performance CPUs and coherent GPUs.
This architecture allows all processors to access and share data directly, crucial for demanding scientific workloads.
The system will also feature an NVIDIA Quantum-X800 InfiniBand networking platform, offering significantly increased in-Network Computing performance for large-scale tasks.
The Doudna system aims to provide over 11,000 researchers with tools for real-time discovery and is expected to be more than 10 times more powerful in scientific output than its predecessor, Perlmutter, using only 2-3 times the power.
This means a 3-5x increase in performance per watt.
This setup is designed not just for speed but for impact, tailored for real-time discovery.
Michael Dell, Chairman and CEO of Dell Technologies, said, “Our collaboration with the Department of Energy on Doudna underscores a shared vision to redefine the limits of high-performance computing and drive innovation that accelerates human progress”.
Doudna’s Unified Approach to AI, Simulation, and Data
A key feature of Doudna is its ability to merge simulation, data, and AI onto a single, seamless platform. “The Doudna supercomputer is designed to accelerate a broad set of scientific workflows,” explained NERSC Director Sudip Dosanjh.
It will connect to DOE experimental and observational facilities via the Energy Sciences Network (ESnet), enabling scientists to stream data directly into the system for near-real-time analysis.
This integration means the supercomputer becomes an active part of the research process.
As Nick Wright, Doudna chief architect at NERSC, put it, “We’re not just building a faster computer. We’re building a system that helps researchers think bigger and discover sooner”.
Key Research Areas to be Accelerated by Doudna Supercomputer
The Doudna supercomputer is poised to revolutionize various research fields:
- Fusion Energy: Advancing simulations that unlock clean fusion energy.
- Materials Science: Enabling AI models to design new classes of superconducting materials.
- Drug Discovery Acceleration: Creating ultrarapid workflows that help biologists fold proteins fast enough to outpace a pandemic. One of the key use cases will be genomics research.
- Astronomy: Allowing real-time processing of data from instruments like the Dark Energy Spectroscopic Instrument at Kitt Peak to help scientists map the universe.
- Fundamental Physics: Aiding researchers like Benjamin Nachman in using AI to analyze particle physics data.
- Quantum Computing: Supporting scalable quantum algorithm development, modeling and verification of quantum computers, and the co-design of future integrated quantum-HPC systems using platforms like NVIDIA CUDA-Q.
NVIDIA founder and CEO Jensen Huang described Doudna as “a time machine for science — compressing years of discovery into days”. He added, “It is the foundation of scientific discovery for our country. It is also the foundation for economic and technology leadership”.
Long-Term Significance of the US Supercomputer Doudna
With its deployment slated for 2026, the US supercomputer Doudna is designed for urgency, aiming to provide the infrastructure needed for the next wave of AI-assisted scientific breakthroughs.
It’s expected to serve over 11,000 scientists and 800 projects annually through the National Energy Research Scientific Computing Center (NERSC).
This system is not just about raw computing power; it’s about creating a new era of integrated discovery, therefore allowing researchers to tackle some of the world’s biggest challenges across numerous fields.
