A Proof of Concept for 10x+ Efficiency Gains for Multi-Sensor Data Fusion Utilizing a Howard Cascade Parallel Processing System
Abstract
Tools and techniques were developed by Massively Parallel Technologies Inc. (MPT) which enable intrinsically non-parallel processing problems to be processed by inexpensive parallel processing architectures. The objective of this contract effort was to create a more effective method for multi-sensor searches, and toward that goal, to improve data fusion and processing capability by greater than 10 times over current capabilities (when compared to the capability as shown in a uniprocessor environment). This objective was met, and the performance speed up yielded a greater than 70 times speed up on a 127-node Howard Cascade RAIS (Redundant Array of Inexpensive Systems). The processing solution implemented is original and innovative; it can be implemented in a non-intrusive manner, yielding accurate results and efficient scaling into existing processing environments, using inexpensive off-the-shelf components. In addition a methodology has been developed that provides for rapid integration of new algorithms into the defined multi-sensor fusion processing solution.
Document Details
- Document Type
- Technical Report
- Publication Date
- Jul 01, 2003
- Accession Number
- ADA417911
Entities
People
- Kevin Howard
Organizations
- Booz Allen Hamilton