OpenGL ES 2.0 programmable 3D graphics pipeline is the current new standard for embedded graphics processor designs. The programmable vertex shader replaces the geometry operations in the previous fixed-function graphics pipeline and provides more flexible APIs for more realistic animation effects. In this thesis, we introduce the OpenGL ES 2.0 specification, and the design of programmable vertex shader architecture and instruction set. In particular, we focus on the integration issues encountered when the vertex shader is integrated with other hardware components and software during the entire SoC design, and verify the vertex shader on FPGA with demonstration.

In order to realize the advanced graphics rendering algorithms which tends to become more complex and flexible, more and more graphics processor units (GPU) include a micro-processor-like core to support the programmable shading capability. However, since the number of cycles spent in the fragment shader in programmable GPU will vary with different applications, the hardware implementation of the remaining fixed function of the graphics rendering flow becomes not trivial because the suitable target throughput is hard to set. In addition, the data transfer between the shader processor and other hardware fixed-function modules will also represent a big overhead. Therefore, this thesis focuses on realizing the rasterization, which is a very important fixed rendering function, and proposes a pure-software solution that can be executed by the shader processor. The pure-software rasterization requires 98 cycles in setup-stage, and an average of 13 cycles per pixel in interpolation-stage. To further accelerate this rasterization, this thesis also proposes an hardware-software codesign which uses a embedded scan-conversion unit to cooperate with the shader processor. This unit costs about 8.5K gates, which occupies only 1.7% of the entire GPU, but can help reduce more than 30% cycles compared with the pure-software approach in the test-benches used in this thesis. The other contribution of this thesis is to implement the stereoscopic graphic rendering function. To provide stereoscopic effect, the graphic rendering system has to run the entire rendering flow for additional passes to generate the results from different views. However, this thesis will embed an additional code in the fragement shader to adjust the x-coordinate position generated by vertex shader to avoid the additional running pass of the vertex shader.

In the field of computer graphics, shaders provide an interface between lights and surfaces, giving the appearance of metal, plastic, wood, etc. As the field progresses, more and more shaders are required to simulate a wider and wider variety of materials. We present a new shader for the simulation of wood burl, a complex material used in furniture, art, car interiors, and a host of other luxury items. This shader was developed through a morphological approach - a study of the original material, its structure, and growth. Consequently, research began with a thorough look at wood burl, polished and unpolished, in an assortment of different species. We discovered the appearance can be broken into three sub-appearances - knots, curl, and a subtle undergrain. These three sub-appearances interact to create the characteristic swirls and whorls of burl. For the subtle undergrain, we used a common oak shader, added noise, and faded it into the background. We then developed a system of randomly placing points through the material to act as knots. Since the knots grow and distort the surrounding grain, we used distance-scaled forces to push the surface coordinates around and between all the knots. When the oak shader is applied, it appears to swirl and curl around the knots, much like a stream between rocks. This created the first level of curl or swirly grained wood, but one level alone appeared flat. To solve this, we procedurally blended levels of curl to give a look of increased depth. Finally, we added reflection, gloss, and other surface properties to give a look of warmth and polish. All of these properties are controlled by a set of parameters in the shader's interface. By adjusting these parameters, the user can emulate a variety of different burl types.

Celtic art contains mysterious and fascinating aesthetic elements including complex knot work motifs. The problem is that creating and exploring these motifs require substantial human effort. One solution to this problem is to create a process that collaboratively uses interactive and procedural methods within a computer graphic environment. Spline models of Celtic knot work can be interactively modeled and used as input into procedural shaders. Procedural shaders are computer programs that describe surface, light, and volumetric appearances to a renderer. The control points of spline models can be used to drive shading procedures such as the coloring and displacement of surface meshes. The result of this thesis provides both an automated and interactive process that is capable of producing complex interlaced structures such as Celtic knot work within a three-dimensional environment.

<p>Målet med detta arbete är att utveckla och utvärdera ett shadergrafsystem med stöd för flera shaderspråk. Fokus ligger på implementationen av en prototyp och hur dess delar fungerar. Prototypen utvärderas med hjälp av ett par experiment för att se hur användbart systemet för datorspel. Experimenten visar att systemet kan användas istället för traditionellt handskrivna shaders och på så vis avlasta programmerare och ge mer kontroll till grafiker.</p>

Målet med detta arbete är att utveckla och utvärdera ett shadergrafsystem med stöd för flera shaderspråk. Fokus ligger på implementationen av en prototyp och hur dess delar fungerar. Prototypen utvärderas med hjälp av ett par experiment för att se hur användbart systemet för datorspel. Experimenten visar att systemet kan användas istället för traditionellt handskrivna shaders och på så vis avlasta programmerare och ge mer kontroll till grafiker.

No description available.

When developing applications in Direct3D today, developers can choose between using the fixed function pipeline and the programmable pipeline. The programmable pipeline is more flexible than the fixed function pipeline, but what is the price for high flexibility? Is high flexibility desired at any cost? How is the choice of pipeline affecting performance? The purpose of this master thesis is to evaluate the performance of the two pipelines. This will be achieved by developing a benchmark program, which measures performance when various graphical effects are tested. The results of the evaluation will hopefully help developers to decide which pipeline to use, in terms of performance. In the end we will see that the fixed function pipeline is faster than the programmable pipeline in all our tests.

<p></p><p>Shader programming is an efficient way to render graphics yet can be complex to understand for emerging computational artists who are new to the world of creative programming. Since shaders are an important part of visual programming, making them easier to use should be considered an important factor in teaching basic to advanced concepts in the rendering pipeline of computer graphics. Though some tools like shader editors and interactive graphical interfaces have been designed to aid in the understanding of these concepts, they still fall behind in some areas in meeting the requirements of emerging computational artists. </p> <p>In this thesis we present and explore the usability of a new Shader Mode tool developed for an open-source software called Processing, widely used in education and production for digital arts and design, and discuss how it can aid shader programming for emerging computational artists. This tool was inspired by a project the author did for Google Summer of Code in 2018. The tool was tested with Processing users who have some familiarity with shader programming. The analysis of the tool was done using a mixed method research technique: combination of quantitative and qualitative analysis. Since we were unable to get enough users for the study, the results could not be generalized to all Processing shader users. However, relevant user feedback is discussed. </p><br><p></p>

The computational capacity of graphics cards for general-purpose computinghave progressed fast over the last decade. A major reason is computational heavycomputer games, where standard of performance and high quality graphics constantlyrise. Another reason is better suitable technologies for programming thegraphics cards. Combined, the product is high raw performance devices andmeans to access that performance. This thesis investigates some of the currenttechnologies for general-purpose computing on graphics processing units. Technologiesare primarily compared by means of benchmarking performance andsecondarily by factors concerning programming and implementation. The choiceof technology can have a large impact on performance. The benchmark applicationfound the difference in execution time of the fastest technology, CUDA, comparedto the slowest, OpenCL, to be twice a factor of two. The benchmark applicationalso found out that the older technologies, OpenGL and DirectX, are competitivewith CUDA and OpenCL in terms of resulting raw performance.