The Mission: Real-Time Monitoring of the Sun

Volume SDO captures an image of the sun every 1.3 seconds, building a repository of over 150 million files and 100 billion detections — totaling more than 20 petabytes of data. NASA scientists use AI-powered algorithms to clean, sort and classify these pixels as good or bad.

Speed Cloud and network limitations made it difficult to extract and analyze over 20 petabytes of data, resulting in multi-year delays. The team first used desktop GPU workstations but had to rely on external USB storage, creating I/O bottlenecks. Cloud clusters offered better scalability but introduced new security challenges.

Security NASA’s mission-critical data is protected by multi-layered security protocols — but those same safeguards can hinder innovation. Strict controls around access, transfer and computation can slow adoption of new technologies in secure data environments.

The Challenge: Volume, Speed and Data Security

Capturing the sun’s surface is just the beginning — the real challenge lies in analyzing over a terabyte of daily data. As the first mission launched under NASA’s Living With a Star Program, the Solar Dynamics Observatory (SDO) uses AI to process and analyze this data in real time. By mapping plasma motions and magnetic activity, SDO helps identify regions prone to solar flares, which can disrupt Earth’s upper atmosphere and interfere with GPS signals.

“The layers of security keep piling up and become a deterrent. It defeats the purpose of having faster, more convenient tools to crunch big data — each set reaching several terabytes. Now, computing TB-sized datasets locally, my momentum isn’t broken by organizational bottlenecks.” Dr. Raphael Attié, Solar Astronomer, NASA Goddard

The previous solution couldn’t deliver the storage, speed or security needed to handle large datasets — delaying results by over a year. NASA required a more capable, compliant infrastructure to accelerate insights and support mission-critical research.

They needed a high-performance, on-premises system:

• Built for AI workflows

• Custom software stacks and strict security protocols — while minimizing delays from data movement.

• GPU and CPU parallel processing was key to maximizing performance along with

• Strong vendor support tailored to NASA’s evolving mission demands

Key Performance Features • Storage and Speed: Fast NVMe and enterprise-class drives process up to 1.5TB per day • Dual Architecture: Dual Xeon CPUs + NVIDIA Quadro RTX 8000 GPUs • Tool Compatibility: Native support for TensorFlow, RAPIDS, CuDF, 3D visualization and more • Bottleneck Reduction: Local compute eliminates I/O constraints and cloud transfer delays

Real-World Impact • The time to train a neural net was reduced from one hour to

just seven minutes. NASA’s SDO team saw faster processing, reduced wait times, and greater interactivity by localizing AI workloads and minimizing dependence on cloud networks. This allowed for greater scalability and flexibility in testing.

Built for Federal IT Environments • Designed to move TB-scale data without relying on the cloud • Designed for mission-critical work with up to 360,000 hours

of rigorous testing. [1]

• Aligned to federal compliance and security posture • Enables fast, secure workflows on-prem • Plug-and-play support streamlines upgrades

Ready to put high-performance AI to work?

The Solution: HP Z8 Workstation “We quickly realized with [desktop workstations] that you can have a high-powered engine, but if you don’t have the transmission (i.e. optimized software stack) to put the power to the road, you know you might as well just give up, because you’re never going to get anywhere.” �Dr. Raphael Attié, Solar Astronomer, NASA Goddard

[1] HP Total Test Process testing is not a guarantee of future performance under these test conditions. Damage under the HP Total Test Process test conditions or any accidental damage requires an optional HP Accidental Damage Protection Care Pack. Military standard testing is not intended to demonstrate fitness of U.S. Department of Defense (DoD) contract requirements or for military use. Select images courtesy of images.nasa.gov.

Intel, the Intel logo, Core and Xeon are trademarks or registered trademarks of Intel Corporation or its subsidiaries in the United States and other countries. Microsoft and Windows are either registered trademarks or trademarks of Microsoft Corporation in the United States and/or other countries.

NVIDIA and Quadro are trademarks and/or registered trademarks of NVIDIA Corporation in the U.S. and other countries. Linux® is the registered trademark of Linus Torvalds in the U.S. and other countries. AMD is a trademark of Advanced Micro Devices, Inc.

© Copyright 2023, 2025 HP Development Company, L.P. The information contained herein is subject to change without notice. The only warranties for HP products and services are set forth in the express warranty statements accompanying such products and services. Nothing herein should be construed as constituting an additional warranty. HP shall not be liable for technical or editorial errors or omissions contained herein.

Talk to a government expert today: discover.hp.com/missionready-workstations

http://images.nasa.gov https://discover.hp.com/missionready-workstations