GPU ray tracing with CUDA

Author

Thomas A. Pitkin, Eastern Washington University

Date of Award

2013

Rights

Access is available to all users

Document Type

Thesis

Degree Name

Master of Science (MS) in Computer Science

Department

Computer Science

Abstract

"Ray Tracing is a rendering method that generates high quality images by simulating how light rays interact with objects in a virtual scene. The ray tracing technique can accurately portray advanced optical effects, such as reflections, refractions, and shadows, but at a greater computational cost and rendering time than other rendering methods. Fortunately, technological advances in GPU computing have provided the means to accelerate the ray tracing process to produce images in a significantly shorter time. This paper attempts to clearly illustrate the difference in rendering speed and design by developing and comparing a sequential CPU and parallel GPU implementation of a ray tracer, written in C++ and CUDA respectively. A performance analysis reveals that the optimized GPU ray tracer is capable of producing images with speedup gains up to 1852X when compared to the former CPU implementation"--Document.

Comments

Typescript. Vita.

Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial-No Derivative Works 4.0 International License.

Recommended Citation

Pitkin, Thomas A., "GPU ray tracing with CUDA" (2013). EWU Masters Thesis Collection. 94.
https://dc.ewu.edu/theses/94