Date of Award

12-2009

Degree Type

Thesis

Degree Name

Master of Science

Major

Computer Science

Major Professor

Michael Vose

Committee Members

James Plank, Michael Berry

Abstract

The Computed Tomography Imaging Spectrometer (CTIS) is a device capable of simultaneously acquiring imagery from multiple bands of the electromagnetic spectrum. Due to the method of data collection from this system, a processing intensive reconstruction phase is required to resolve the image output. This paper evaluates a parallelized implementation of the Vose-Horton CTIS reconstruction algorithm using the Cell processor. In addition to demonstrating the feasibility of a mixed precision implementation, it is shown that use of the parallel processing capabilities of the Cell may provide a signi cant reduction in reconstruction time.

Files over 3MB may be slow to open. For best results, right-click and select "save as..."

Share

COinS