GPU ray tracing with CUDA

<p>"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.</p>

Name thesis:degree_name

Master of Science (MS) in Computer Science

Level thesis:degree_level

Thesis

Discipline thesis:degree_discipline

Computer Science

Year

2013

Author dc:creator

• Pitkin, Thomas A.

• Parallel programming (Computer science)
• Parallel processing (Electronic computers)
• Rendering (Computer graphics)
• Ray tracing algorithms
• CUDA (Computer architecture)
• Computer graphics
• Computer Sciences

Statement dc:rights

• Access is available to all users

Repository record dc:identifier

https://dc.ewu.edu/theses/94

OAI identifier oai:identifier

oai:dc.ewu.edu:theses-1093