System Management Services for High-Performance In-situ Aerospace Computing

With the ever-increasing demand for higher bandwidth and processing capacity of today’s space exploration, space science, and defense missions, the ability to efficiently apply commercial-off-the-shelf technology for on-board computing is now a critical need. In response to this need, NASA’s New Millennium Program office has commissioned the development of the Dependable Multiprocessor for use in payload and robotic missions. The Dependable Multiprocessor system provides power-efficient, high-performance, faulttolerant cluster computing resources in a cost-effective and scalable manner. As a major step toward the flight system to be launched in 2009, Honeywell and the University of Florida have successfully investigated and developed a management system and associated middleware components to make the processing of science-mission data as easy in space as it is in ground-based clusters. This paper provides a detailed description of the Dependable Multiprocessor’s middleware technology and experimental results validating the concept and demonstrating the system’s scalability even in the presence of faults.