Streaming Model Based Volume Ray Casting Implementation for Cell Broadband Engine

Abstract

Interactive high quality volume rendering is becoming increasingly more important as the amount of more complex volumetric data steadily grows. While a number of volumetric rendering techniques have been widely used, ray casting has been recognized as an effective approach for generating high quality visualization. However, for most users, the use of ray casting has been limited to datasets that are very small because of its high demands on computational power and memory bandwidth. However the recent introduction of the Cell Broadband Engine (Cell B.E.) processor, which consists of 9 heterogeneous cores designed to handle extremely demanding computations with large streams of data, provides an opportunity to put the ray casting into practical use. In this paper, we introduce an efficient parallel implementation of volume ray casting on the Cell B.E. The implementation is designed to take full advantage of the computational power and memory bandwidth of the Cell B.E. using an intricate orchestration of the ray casting computation on the available heterogeneous resources. Specifically, we introduce streaming model based schemes and techniques to efficiently implement acceleration techniques for ray casting on Cell B.E. In addition to ensuring effective SIMD utilization, our method provides two key benefits: there is no cost for empty space skipping and there is no memory bottleneck on moving volumetric data for processing. Our experimental results show that we can interactively render practical datasets on a single Cell B.E. processor.

Irregular Grid Raycasting Implementation on the Cell Broadband Engine

“…They implemented a raycasting for terrain rendering, where again, only the surface data is considered. The recent work by Kim and Jaja [26] is the most related to ours. They implemented the raycasting algorithm on the Cell processor, which, however, only handles regular datasets.…”

“…The impressive gains obtained by the raycasting implementation for regular datasets in the Cell BE proposed by Kim and Jaja in [26], however, cannot be reproduced for irregular datasets. Their implementation obtained huge accelerations with two special optimizations, approximation and refining, that removed memory latency overheads.…”

Developing serious games for cultural heritage: a state-of-the-art review

“…These may be aligned to always face the viewer as billboards [1], a common game technique with a variety of uses [197], or a series of these may be used to slice through a full volume at regular intervals. An alternative method for rendering full volumes is ray-marching, where a volume is sampled at regular intervals along a viewing ray, which can now be implemented in a shader [34], or on processors that are now being used in games consoles [92].…”

Exploring parallelism in volume ray casting

“…The power of the Cell BE processor has been exploited in [2] for ray casting of irregular grids and in [27] for regular grids. None of these previous work, however, explored the particularities of different accelerators architectures to improve the memory bound process of the ray traversing in a irregular grid ray casting.…”