A highly flexible multiprocessor solution for ray tracing

The ray tracing algorithm continues to attract much research and development to improve the quality of the images that are generated, and to reduce the time taken to produce them. By identifying the key requirements of a development system from the user's point of view, we describe a general-purpose multiprocessor solution for ray tracing which may be used to reduce execution time without restricting development of the ray tracing code. The solution is based upon a distributed memory multiprocessor system in which each processor addresses a small amount of memory relative to the size of the model database. Methods for exploiting the coherence of references to entries in the database are described which use a combination of dynamic and static caching techniques. This scheme allows databases of arbitrary size to be supported on multiprocessors with limited distributed memory.     

Parallel processing of incremental ray tracing on a shared-memory multiprocessor

This paper presents a novel parallel-processing method for image synthesis using incremental ray tracing on a shared-memory multiprocessor workstation. The most efficient technique for image synthesis is ray tracing, proposed by Whitted in 1980. Ray-tracing algorithms are simple and can generate realistic images. However, they are time-consuming, since calculations of the intersections between objects and ray increase exponentially as the complexity of scenes increases. Fast image synthesis for animation is one of the most important topics in computer graphics. As the area of computer applications has broadened, the complexity of images to be synthesized has increased. Parallel processing of computer graphics is one way of achieving fast image synthesis. This paper describes a parallel processing technique for incremental ray tracing, which recalculates only the rays changed by moving objects in successive scenes of continuous image synthesis. The performance of parallel ray tracing was evaluated on the multiprocessor workstation TOP-1. Strategies for allocating pixels to processes under a multiprocess operating system on this workstation are discussed.     

Two algorithms for taking advantage of temporal coherence in ray tracing

The basic ray-tracing algorithm is adapted to make ray-tracing faster for the production of motion pictures. Two algorithms are presented. The image space temporal coherence algorithm takes advantage of the fact that motion picture images do not change very much from frame to frame. The reprojection algorithm uses information about the object space saved from the previous frame to accelerate the processing of the current frame. The reprojection algorithm is used when the viewpoint of the current frame is changed by a small amount from the viewpoint of the previous frame.     

Spacetime ray tracing for animation

Techniques for the efficient ray tracing of animated scenes are presented. They are based on two central concepts: spacetime ray tracing, and a hybrid adaptive space subdivision/boundary volume technique for generating efficient, nonoverlapping hierarchies of bounding volumes. In spacetime ray tracing, static objects are rendered in 4-D space-time using 4-D analogs to 3-D techniques. The bounding volume hierarchy combines elements of adaptive space subdivision and bounding volume techniques. The quality of hierarchy and its nonoverlapping character make it an improvement over previous algorithms, because both attributes reduce the number of ray/object intersections that must be computed. These savings are amplified in animation because of the much higher cost of computing ray/object intersections for motion-blurred animation. It is shown that it is possible to ray trace large animations more quickly with space-time ray tracing using this hierarchy than with straightforward frame-by-frame rendering     

Pixel-selected ray tracing

An acceleration method based on an idea that T. Whitted (Commun. ACM, vol.23, no.6 pp.343-349, June 1980) presented on ray tracing is discussed. He proposed making antialiased images by hierarchical adaptive oversampling. The present authors use hierarchical adaptive undersampling to reduce the number of pixels whose intensity must be calculated by ray tracing. To implement pixel-selected ray tracing (PSRT), homogeneous regions in images must first be found. Generally, adaptive undersampling can result in some image-quality defects, because small objects and parts of thin or wedge-shaped objects may disappear when they are located between the initially sampled pixels. PSRT has an improved algorithm that uses pixels with the correct object information from among the sampled pixels to find pixels with erroneous color and correct them. Moreover, PRST uses ray-object intersection trees for precise classification of the homogeneity of regions and for fast intensity calculation in homogeneous regions. Experimental results are presented. They show that PSRT is two to nine times faster than standard ray tracing     

Discrete ray tracing

Discrete ray tracing, or 3-D raster ray tracing (RRT), which, unlike existing ray tracing methods that use geometric representation for the 3-D scene employs a 3-D discrete raster of voxels for representing the 3-D scene in the same way a 2-D raster of pixels represents a 2-D image, is discussed. Each voxel is a small quantum unit of volume that has numeric values associated with it representing some measurable properties or attributes of the real object or phenomenon at that voxel. It is shown that RRT operates in two phases: preprocessing voxel and discrete ray tracing. In the voxel phase, the geometric model is digitized using 3-D scan-conversion algorithms that convert the continuous representation of the model into a discrete representation within the 3-D raster. In the second phase, RRT employs a discrete variation of the conventional recursive ray tracer in which 3-D discrete rays are traversed through the 3-D raster to find the first surface voxel. Encountering a nontransparent voxel indicates a ray-surface hit. Results obtained by running the RRT software one one 20-MIPS (25-GHz) processor of a Silicon Graphics 4D/240GTX are presented in terms of CPU time     

Interactive ray tracing for volume visualization

Presents a brute-force ray-tracing system for interactive volume visualization. The system runs on a conventional (distributed) shared-memory multiprocessor machine. For each pixel, we trace a ray through a volume to compute the color for that pixel. Although this method has a high intrinsic computational cost, its simplicity and scalability make it ideal for large data sets on current high-end parallel systems. To gain efficiency, several optimizations are used, including a volume bricking scheme and a shallow data hierarchy. These optimizations are used in three separate visualization algorithms: isosurfacing of rectilinear data, isosurfacing of unstructured data, and maximum-intensity projection on rectilinear data. The system runs interactively (i.e. at several frames per second) on an SGI Reality Monster. The graphics capabilities of the Reality Monster are used only for display of the final color image     

Adaptive cell division for ray tracing

In ray tracing the two most commonly used data structures are the octree and uniform cell division. The octree structure allows efficient adaptive subdivision of space, while taking care of the spatial coherence of the objects in it; however, the tree structure locating the next node in the path of a ray is complex and time consuming. The cell structure, on the other hand, can be stored in a three-dimensional array, and each cell can be efficiently accessed by specifying three indices. However, such a uniform cell division does not take care of object coherence. The proposed data structure combines the positive features of the above data structures while minimising their disadvantages. The entire object space is implicitly assumed to be a three-dimensional grid of cells. Initially, the entire object space is a single voxel which later undergoes “adaptive cell division.” But, unlike in the octree structure, where each voxel is divided exactly at the middle of each dimension, in adaptive cell division, each voxel is divided at the nearest cell boundary. The result is that each voxel contains an integral number of cells along each axis. Corresponding to the implicit cell division we maintain a three-dimensional array, with each array element containing the voxel number which is used to index into the voxel array. The voxel array is used to store information about the structure of each voxel, in particular, the objects in each voxel. While a ray moves from one voxel to another we always keep track of the cell through which the ray is currently passing. Since only arrays are involved in accessing the next voxel in the path of the ray, the operation is very efficient.     

Efficient data management for incoherent ray tracing

To obtain good performance on the GPU hardware, it is necessary to design algorithms to manage data, access memory under GPU memory hierarchy, and schedule more efficient threads. In this paper, we propose an efficient data management and task management designed for GPU based ray tracing. Due to the dynamic and uncertainty in ray tracing, we design data-management layer and task-management layer combined with fuzzy spatial analysis, use the two-level ray sorting and a ray bucket structure to reorganize ray data, then a warp's threads can be scheduled to access coherent geometry and nodes data, reduce memory bandwidth, and dispatch the data locally. We schedule tasks in data-driven execution according to coherent data, propose an adaptive ray compaction to eliminate inactive threads, maintain task efficiency of threads in a warp, and design two heuristics to decrease the compaction cost. On the basis of it, we also introduce a memory-optimized dynamic traversal management to reduce incoherent memory access, and avoid frequent sorting computation and compaction operations. Our experiments demonstrate all of these work combined can achieve good performance.     

Heuristics for ray tracing using space subdivision

Ray tracing requires testing of many rays to determine intersections with objects. A way of reducing the computation is to organize objects into hierarchical data structures. We examine two heuristics for space subdivisions using bintrees, one based on the intuition that surface area is a good estimate of intersection probability, one based on the fact that the optimal splitting plane lies between the spatial median and the object median planes of a volume. Traversal algorithms using cross links between nodes are presented as generalizations of ropes in octrees. Simulations of the surface area heuristic and the cross link scheme are presented. These results generalize to other hierarchical data structures.     

An efficient hierarchicaltraversal algorithm for ray tracing

Ray tracing has been shown to be an excellent technique for rendering realistic images. However, it is important to reduce the lengthy computation time resulting from the brute-force nature of the original ray-tracing algorithms. In this paper, two ideas are proposed to speep up the well-known hierarchical subdivision method. First, a new hierarchy traversal scheme is described to reduce the number of raybounding volume intersection tests for secondary rays. Then, a plane-sweep method is proposed to make fewer intersection checks for eye rays. Experiments and discussions are presented to prove the feasibility of our methods.     

Improved techniques for ray tracing parametric surfaces

Several techniques for acceleration of ray tracing parametric surfaces are presented. Some of these are entirely new to ray tracing, while others are improvements of previously known techniques. First a uniform spatial subdivision scheme is adapted to parametric surfaces. A new space- and time-efficient algorithm for finding raysurface intersections is introduced. It combines numerical and subdivision techniques, thus allowing utilization of ray coherence and greatly reducing the average ray-surface intersection time. Non-scanline sampling orders of the image plane are proposed that facilitate utilization of coherence. Finally, a method to handle reflected, refracted, and shadow rays in a more efficient manner is described. Results of timing tests indicating the efficiency of these techniques for various environments are presented.     

Adaptive undersampling for efficient mobile ray tracing

Aiming to develop an efficient ray tracer for a mobile platform, we present an adaptive undersampling method that enhances the rendering speed by effectively replacing expensive ray-tracing operations with cheap interpolation whenever possible. Our method explores both object- and image-space information gathered during ray tracing to detect possibly problematic pixels. Rays are fired only for these pixels. We also present a postcorrection algorithm that minimizes annoying artifacts inevitably caused by undersampling. Our implementation on a mobile GPU demonstrates that this method can speed up the rendering computation significantly, while retaining almost the same visual quality of the rendering.     

Improving multiprocessor performance with fine-grain coherence bypass

Efficient and scalable cache coherence protocol is crucial to high-performance servers with sharedmemory. The directory-based cache coherence protocol is more desirable than the snooping-based protocol with respect to the scalability. However, even for the former protocol, scaling to a large number of cores is also challenging due to the additional area requirements of the directories. We observed that a significant percentage of the referenced memory blocks were only accessed by a single core(even in parallel applications) which could be considered as private memory blocks. An intuitive motivation from this observation is that memory blocks accessed by a single core do not require coherence maintenance. The issue is to identify the private block and track the change of its access pattern. We propose a novel hardware approach to(1) dynamically identify the shared memory blocks at the cache block level, and(2) bypass the coherence procedure for the private memory blocks. This approach increases the effectiveness of the directory-based approach and therefore improves the system performance. Experimental results showed that, our approach can on an average(1) avoid the coherence tracking of about 54% referenced memory blocks,(2) reduce the coherence overhead by 77%,(3) avoid 8% L2 cache misses, and(4) shorten the execution time of parallel applications by 13%.     

Coherent multiresolution isosurface ray tracing

We implement and evaluate a fast ray tracing method for rendering large structured volumes. Input data is losslessly compressed into an octree, enabling residency in CPU main memory. We cast packets of coherent rays through a min/max acceleration structure within the octree, employing a slice-based technique to amortize the higher cost of compressed data access. By employing a multiresolution level of detail (LOD) scheme in conjunction with packets, coherent ray tracing can efficiently render inherently incoherent scenes of complex data. We achieve higher performance with lesser footprint than previous isosurface ray tracers, and deliver large frame buffers, smooth gradient normals and shadows at relatively lesser cost. In this context, we weigh the strengths of coherent ray tracing against those of the conventional single-ray approach, and present a system that visualizes large volumes at full data resolution on commodity computers.     

Integrating cache coherence protocols for heterogeneous multiprocessor systems. 1

This systematic methodology maintains cache coherency in a heterogeneous shared-memory multiprocessor system on a chip. It works with any combination of processors that support any invalidation-based protocol, and experiments have demonstrated up to a 51 percent performance improvement, compared to a pure software solution.     

Who invented ray tracing?

We provide some remarks on the very early developments of the visualization techniques conducted during the European Renaissance. It is shown that the basic principle of ray tracing was already presented by Albrecht Dürer (1471–1528) in 1525. This article is intended to be of common interest; it is not a scientific report.