The Ray Tracing Visualization Toolkit (rtVTK) is a collection of programming and visualization tools supporting the visual analysis of algorithms that implement ray-based computations. rtVTK enables investigators to explore the computational elements of such algorithms via layered visualization within the spatial domain of computation. Client programs utilize a library for recording and processing ray state, and an interactive GUI integrates a configurable pipeline of loosely coupled components to allow run-time control of the resulting visualizations.

This talk will provide an overview of rtVTK, including its goals and the key components of its software architecture. We will also discuss two areas in computer graphics to which ray state visualization with rtVTK has been applied successfully. Finally, we will speculate on the role of ray state visualization generally—and rtVTK specifically—in advanced, non-graphics applications such as ballistic penetration simulations.

Stream filtering is an approach to coherent ray tracing that recasts the basic algorithm as a series of conditional operations, or stream filters, designed to exploit coherence in arbitrarily-sized groups of arbitrary rays, or ray streams.  These filters partition streams into active and inactive subsets throughout rendering, isolating and processing only those rays exhibiting some property of interest in a given stage.  The core operations in ray tracing—including traversal, intersection, and shading—can be written as a sequence of stream filters that eliminate inactive elements and maximize coherence in later operations.

This talk will provide an overview of stream filtered ray tracing, including some highlights of StreamRay, a multicore SIMD microarchitecture that delivers frame rates of 15-32 frames/second for scenes of high geometric complexity rendered with Kajiya-style path tracing.  We will also discuss recent results from an ongoing analysis of the bandwidth requirements imposed by the approach and speculate about the design of an ideal memory hierarchy for ray-based graphics architectures that implement stream filtered ray tracing.

The current progression of commodity processing architectures exhibits a trend toward increasing parallelism, requiring that undergraduate students in a wide range of technical disciplines gain an understanding of problem solving in massively parallel environments.  However, as a small comprehensive college, we cannot currently afford to dedicate an entire semester-long course to the study of parallel computing.  To combat this situation, we have integrated the key components of such a course into a 300-level course on modern operating systems.  In this paper, we describe a parallel computing unit that is designed to dovetail with the discussion of process and thread management common to operating systems courses.  We also describe a set of self-contained projects in which students explore two parallel programming models, POSIX Threads and NVIDIA’s Compute Unified Device Architecture, that enable parallel architectures to be utilized effectively.  In our experience, this unit can be integrated with traditional operating systems topics quite readily, making parallel computing accessible to undergraduate students without requiring a full course dedicated to these increasingly important topics.

This paper also appears in the proceedings of the 2009 ASEE Annual Conference and Exposition, June 2009.