Follow this link to skip to the main content
NASA Logo - Jet Propulsion Laboratory JPL NASA Caltech


BRING THE UNIVERSE TO YOU:    JPL Email News    News    RSS    Podcast    Video

JPL Home Earth Solar System Stars & Galaxies Technology
Distributed Spacecraft Technology
Formation Modeling Formation Sensors Formation Control Metrology Thrusters
Ranging Test Beds Tethers Balloons Autonomy
DST Home
Task Objective and Statement of Work
Task Manager and Team
Industry and Academia Partners
Published Technical Papers
Testbeds and Research Facilities

Formation Modeling


Our research in formation modeling and simulation depends on the use of high-speed, distributed computation resources for research validation, experimentation and design space exploration, and preparation of algorithms and products for infusion into other programs. To this end we have constructed several low-cost supercomputers, modelled on the Beowulf-class supercomputers pioneered by Donald Becker at NASA's Goddard Space Flight Center.

The first of these was a 12-CPU cluster computer constructed from independent off-the-shelf PC computers. Connected by an ordinary private Ethernet switched network, this proof-of-concept computer was used to test various communication, synchronization, and other attributes of cluster computing critical to high-speed simulation.

ShuttlePC clusterViewfinder (seen at right, bottom of rack) is one of our current cluster computer testbeds. Constructed of five dual-cpu machines, it contains 10 Athlon MP 1800+ processors, 10 gigbytes of RAM, and 0.8 Terabytes of disk storage. For connectivity, it includes a dual-bonded, switched, fast-ethernet backbone, and additionally has a 1.3 gigabit, low-latency SCI backplane as well. Our 5-spacecraft formation simulator reaches maximum performance on this cluster, utilizing all ten CPUs.

Our innovative ShuttlePC cluster (seen at right, top of rack) consists of 12 single-cpu Shuttle XPC SS-40G small form-factor (SFF) computers, each housing an Athlon 1800+ CPU, 512 Megabytes of RAM, and not much else. These diskless nodes are connected via switched fast ethernet to a Shuttle XPC SK-41G master that serves as a boot host. This diskless configuration allows us to upgrade the cluster software and OS by simply rebooting the system after upgrading the master node. A spare master node makes it easy to split this cluster into portable testbeds for demonstration purposes.

Credits  Feedback  Related Links  Sitemap
Image Policy   NASA Home Page

Site Manager: Dr. Fred Hadaegh
Webmaster: Kirk Munsell
Updated: November 19, 2003