Philipp Slusallek

RPU: a programmable ray processing unit for realtime ray tracing

Recursive ray tracing is a simple yet powerful and general approach for accurately computing global light transport and rendering high quality images. While recent algorithmic improvements and optimized parallel software implementations have increased ray tracing performance to realtime levels, no compact and programmable hardware solution has been available yet.This paper describes the architecture and a prototype implementation of a single chip, fully programmable Ray Processing Unit (RPU). It combines the flexibility of general purpose CPUs with the efficiency of current GPUs for data parallel computations. This design allows for realtime ray tracing of dynamic scenes with programmable material, geometry, and illumination shaders.Although, running at only 66 MHz the prototype FPGA implementation already renders images at up to 20 frames per second, which in many cases beats the performance of highly optimized software running on multi-GHz desktop CPUs. The performance and efficiency of the proposed architecture is analyzed using a variety of benchmark scenes.

Interactive global illumination using fast ray tracing

Rasterization hardware provides interactive frame rates for rendering dynamic scenes, but lacks the ability of ray tracing required for efficient global illumination simulation. Existing ray tracing based methods yield high quality renderings but are far too slow for interactive use. We present a new parallel global illumination algorithm that perfectly scales, has minimal preprocessing and communication overhead, applies highly efficient sampling techniques based on randomized quasi-Monte Carlo integration, and benefits from a fast parallel ray tracing implementation by shooting coherent groups of rays. Thus a performance is achieved that allows for applying arbitrary changes to the scene, while simulating global illumination including shadows from area light sources, indirect illumination, specular effects, and caustics at interactive frame rates. Ceasing interaction rapidly provides high quality renderings.

Interactive Distributed Ray Tracing of Highly Complex Models

Many disciplines must handle the creation, visualization, and manipulation of huge and complex 3D environments. Examples include large structural and mechanical engineering projects dealing with entire cars, ships, buildings, and processing plants. The complexity of such models is usually far beyond the interactive rendering capabilities of todays 3D graphics hardware. Previous approaches relied on costly preprocessing for reducing the number of polygons that need to be rendered per frame but suffered from excessive precomputation times —often several days or even weeks. In this paper we show that using a highly optimized software ray tracer we are able to achieve interactive rendering performance for models up to 50 million triangles including reflection and shadow computations. The necessary preprocessing has been greatly simplified and accelerated by more than two orders of magnitude. Interactivity is achieved with a novel approach to distributed rendering based on coherent ray tracing. A single copy of the scene database is used together with caching of BSP voxels in the ray tracing clients.

Realtime Ray Tracing on GPU with BVH-based Packet Traversal

Recent GPU ray tracers can already achieve performance competitive to that of their CPU counterparts. Nevertheless, these systems can not yet fully exploit the capabilities of modern GPUs and can only handle medium-sized, static scenes. In this paper we present a BVH-based GPU ray tracer with a parallel packet traversal algorithm using a shared stack. We also present a fast, CPU-based BVH construction algorithm which very accurately approximates the surface area heuristic using streamed binning while still being one order of magnitude faster than previously published results. Furthermore, using a BVH allows us to push the size limit of supported scenes on the GPU: We can now ray trace the 12.7 million triangle Power Plant at 1024 times 1024 image resolution with 3 fps, including shading and shadows.

SaarCOR: a hardware architecture for ray tracing

The ray tracing algorithmis well-known for its ability to generate high-quality images and its flexibility to support advanced rendering and lighting effects. Interactive ray tracing has been shown to work well on clusters of PCs and supercomputers but direct hardware support for ray tracing has been difficult to implement.In this paper, we present a new, scalable, modular, and highly efficient hardware architecture for real-time ray tracing. It achieves high performance with extremely low memory bandwidth requirements by efficiently tracing bundles of rays. The architecture is easily configurable to support a variety of workloads. For OpenGL-like scenes our architecture offers performance comparable to state-of-the-artrasterization chips. In addition, it supports all the usual ray tracing features including exact shadows, reflections, and refraction and is capable of efficiently handling complex scenes with millions of triangles. The architecture and its performance in different configurations is analyzed based on cycle-accurate simulations.

XML3D: interactive 3D graphics for the web

Web technologies provide the basis to distribute digital information worldwide and in realtime but they have also established the Web as a ubiquitous application platform. The Web evolved from simple text data to include advanced layout, images, audio, and recently streaming video. Today, as our digital environment becomes increasingly three-dimensional (e.g. 3D cinema, 3D video, consumer 3D displays, and high-performance 3D processing even in mobile devices) it becomes obvious that we must extend the core Web technologies to support interactive 3D content. Instead of adapting existing graphics technologies to the Web, XML3D uses a more radical approach: We take todays Web technology and try to find the minimum set of additions that fully support interactive 3D content as an integral part of mixed 2D/3D Web documents. XML3D enables portable cross-platform authoring, distribution, and rendering of and interaction with 3D data. As a declarative approach XML3D fully leverages existing web technologies including HTML, Cascading Style Sheets (CSS), the Document Object Model (DOM), and AJAX for dynamic content. All 3D content is exposed in the DOM, fully supporting DOM scripting and events, thus allowing Web designers to easily apply their existing skills. The design of XML3D is based on modern programmable graphics hardware, e.g. supports efficient mapping to GPUs without maintaining copies. It also leverages a new approach to specify shaders independently of specific rendering techniques or graphics APIs. We demonstrated the feasibility of our approach by integrating XML3D support into two major open browser frameworks from Mozilla and WebKit as well as providing a portable implementation based on JavaScript and WebGL.

Realtime ray tracing of dynamic scenes on an FPGA chip

Realtime ray tracing has recently established itself as a possible alternative to the current rasterization approach for interactive 3D graphics. However, the performance of existing software implementations is still severely limited by todays CPUs, requiring many CPUs for achieving realtime performance.In this paper we present a prototype implementation of the full ray tracing pipeline on a single FPGA chip. Running at only 90 MHz it achieves realtime frame rates of 20 to 60 frames per second over a wide range of 3D scenes and includes support for texturing, multiple light sources, and multiple levels of reflection or transparency. A particular interesting feature of the design in the re-use of the transformation unit necessary for supporting dynamic scenes also for other tasks, including efficient ray-triangle intersection as well as shading computations. Despite the additional support for dynamic scenes this approach reduces the overall hardware cost by 68%.We evaluate the design and its implementation across a wide set of example scenes and demonstrate the benefits of dedicated realtime ray tracing hardware.

Distributed interactive ray tracing of dynamic scenes

Recently developed interactive ray tracing systems combine the high performance of todays CPUs with new algorithms and implementations to achieve a flexible and high-performance rendering system offering high-quality, but nonetheless interactive 3D graphics. However, due to its history in offline rendering, interactive ray tracing is usually limited to static scenes and simple walkthroughs. In order to become truly interactive ray tracing must efficiently support dynamic scenes. We present a simple and practical method that allows to interactively ray trace dynamic scenes in a distributed PC cluster environment. Our method separates the scene into independent objects with common properties concerning dynamic updates - similar to OpenGL display lists and scene graph libraries. Three classes of objects are distinguished: static objects are treated as before, objects undergoing affine transformations are handled by transforming rays, and objects with unstructured motion are rebuilt whenever necessary. We present performance and scalability results of our system using a variety of test scenes stressing a wide range of dynamic behaviour.

Experiences with Streaming Construction of SAH KD-Trees

A major reason for the recent advancements in ray tracing performance is the use of optimized acceleration structures, namely kd-trees based on the surface area heuristic (SAH). Though algorithms exist to build these search trees in O(n log n), the construction times for larger scenes are still high and do not allow for rebuilding the kd-tree every frame to support dynamic changes. In this paper we propose modifications to previous kd-tree construction algorithms that significantly increase the coherence of memory accesses during construction of the kd-tree. Additionally we provide theoretical and practical results regarding conservatively sub-sampling of the SAH cost function

Light transport simulation with vertex connection and merging

Developing robust light transport simulation algorithms that are capable of dealing with arbitrary input scenes remains an elusive challenge. Although efficient global illumination algorithms exist, an acceptable approximation error in a reasonable amount of time is usually only achieved for specific types of input scenes. To address this problem, we present a reformulation of photon mapping as a bidirectional path sampling technique for Monte Carlo light transport simulation. The benefit of our new formulation is twofold. First, it makes it possible, for the first time, to explain in a formal manner the relative efficiency of photon mapping and bidirectional path tracing, which have so far been considered conceptually incompatible solutions to the light transport problem. Second, it allows for a seamless integration of the two methods into a more robust combined rendering algorithm via multiple importance sampling. A progressive version of this algorithm is consistent and efficiently handles a wide variety of lighting conditions, ranging from direct illumination, diffuse and glossy inter-reflections, to specular-diffuse-specular light transport. Our analysis shows that this algorithm inherits the high asymptotic performance from bidirectional path tracing for most light path types, while benefiting from the efficiency of photon mapping for specular-diffuse-specular lighting effects.