Spaceborne Computer-2 sets a new benchmark for AI and ML on the ISS
by Clarence Oxford
Los Angeles California (SPX) February 06, 2024
Hewlett Packard Enterprise (NYSE: HPE) has taken a significant step forward in space computing by sending the third iteration of its space computer to the International Space Station (ISS). This event marks a pivotal moment in the evolution of high-performance computing (HPC) capabilities beyond Earth’s atmosphere, leveraging commercial off-the-shelf (COTS) servers. The final voyage of the HPE Spaceborne Computer-2 aboard a SpaceX Falcon 9 rocket, part of a NASA-contracted Northrop Grumman Commercial Resupply Services mission, represents a quantum leap in the scope and complexity of computing tasks that can be performed in space, including artificial tasks. intelligence (AI) and machine learning (ML) workloads.
This iteration of the Spaceborne Computer, built on award-winning HPE Edgeline and ProLiant servers, features an unprecedented upgrade with over 130TB of flash storage from KIOXIA. This enhancement not only represents the largest storage capacity ever sent to the ISS for a single mission, but also facilitates the execution of new types of applications and research using larger data sets through the National Laboratory of the ISS. The inclusion of 960 GB KIOXIA RM Series Value SAS SSDs, 1024 GB XG Series NVMe SSDs, and 30.72 TB PM6 Enterprise SAS SSDs demonstrates the system’s readiness for advanced research tasks.
The Spaceborne Computer-2’s advancements aren’t limited to storage. Updates to the operating system, NASA spaceflight support software, and system security measures have been implemented, ensuring that system performance in the harsh conditions of space is meticulously maintained. monitored after its installation on board the ISS.
One of the most notable advantages of this onboard supercomputer is its ability to significantly reduce the need for large-scale data downloads on Earth. By processing data in low Earth orbit, researchers can reduce download size by 30,000 times by transmitting only essential data or information. This capability is critical to advancing terrestrial and space research, enabling near real-time data evaluation and significantly shortening the feedback loop for scientific discovery.
The research program for the HPE Spaceborne Computer-2 includes conducting a federated learning (FL) experiment. This experiment aims to independently train ML models and inference engines initially developed in the cloud. By collaborating with cloud service providers, the experiment aims to improve ML training models used on Earth while maintaining an AI inference engine in space. This dual-purpose initiative highlights the potential of space computing to contribute to advances in AI and ML, both in orbit and on the ground.
Additionally, HPE opened the door to public engagement by soliciting proposals for experiments to be conducted on the Spaceborne Computer-2 through the ISS National Laboratory. This initiative provides an unprecedented opportunity for researchers and the public to directly contribute to advances in space research and computing.
The deployment of the HPE Spaceborne Computer-2 to the ISS represents a significant milestone in the use of space for advanced computing research. By leveraging cutting-edge technology and fostering collaborative research initiatives, HPE continues to push the boundaries of what is possible in spatial computing, opening new avenues for scientific discovery and technological innovation.
Related links
Hewlett Packard Company
Space Technology News – Applications and Research
