Dependable Multiprocessor or DM technology was developed as a way of enabling high-performance Commercial-Off-The-Shelf (COTS)processing systems to effectively operate in a space environment. DM technology is an architecture and software framework that enables the latest COTS processing systems to operate in inhospitable environments by providing software-based fault-tolerance. A DM system is a scalable cluster of processors with a highspeed interconnect and an application and hardware independent fault tolerant middleware. The objective of the DM7 flight experiment was to build, test, and demonstrate DM technology in a space environment. DM7 was launched to the ISS on December 2016. The experiment was activated in April 2017 running on-orbit checkouts, experiments, and capturing and compressing camera images. DM operation was successfully demonstrated on-orbit, reaching TRL-7. DM is a pervasive technology applicable to almost any application where highperformance rad-tolerant or fault-tolerant computing is required. Numerous applications have been developed and demonstrated on a variety of DM platforms. Potential applications include: intelligent data mining and data compression, autonomous navigation, autonomous operation & control, advanced space-based networked communication, sophisticated earth observation, astrophysics, and ground-commanded programmable image compression amongst others. The demonstrated applications show the breadth, flexibility, scalability, ease of use, low overhead, and processing potential of DM technology. Following a brief overview of DM technology and a brief overview of the DM7 flight experiment including the most recent post-flight analysis, the paper focuses on past and future DM high performance computing applications. 123


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    High Performance Computing Applications in Space with DM Technology


    Contributors:


    Publication date :

    2019-03-01


    Size :

    1860698 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    High Performance Space Computing

    Rooks, John W. / Linderman, Richard | IEEE | 2007


    High-Performance Computing Challenges in Aeronautics and Space Applications

    Basermann, Achim | German Aerospace Center (DLR) | 2017

    Free access