This is another update of the articles "Fragment Shader Interlock Performance (α Compositing)" and "Fragment Shader Interlock Performance on the Steam Deck", where I previously had a look at the performance of a GPU feature called fragment shader interlock for alpha composition. In the first article, I was not able to test the performance on AMD GPUs, as the fragment shader …

When I supervised a student implementing different image denoisers into my line renderer LineVis, we faced the problem that SVGF, one of the most often used denoisers for real-time path traced applications, is dependent on ∇z(p), which the paper describes as the "gradient of clip-space depth with respect to screenspace coordinates"1 at the point p. It is used in formula (3) of the paper …

This is an update of the article "Fragment Shader Interlock Performance (α Compositing)", where I previously had a look at the performance of a GPU feature called fragment shader interlock for alpha composition. In this article, I said: I would love to also test whether fragment shader interlock also comes out as the performance winner on AMD hardware, but unfortunately AMD does not …

A student I'm currently supervising found an interesting phenomenon on NVIDIA GPUs. When using trilinear interpolation with a 3D texture in Vulkan, the interpolation will not return interpolated values less than 1/2048, even if the texture stores 32-bit floating point values. In the image below, you can see a test case I created where a very small step size is used for volumetric path tracing and …

Over the last decades, how GPUs can be used radically evolved. In the olden days™, GPUs had specialized units for vertex and fragment processing. Due to multiple reasons, one being that different applications may utilize these different types of units to different degrees, a shift to unified units happened that would perform both vertex and fragment processing. For a more in-depth view on the …

In the WebGL canvas in this article, the user can visualize conic sections by altering the coefficients of the formula above the canvas. The conic section is shown for z = 1. Conic sections are defined by the quadratic form ax² + by² + 2cxy + 2dxz + 2eyz + fz² = 0. Aliasing is reduced by implementing rudimentary anisotropic filtering as discussed in …

For the lecture Image Synthesis at the TU München, I adapted the two algorithms shadow volumes and shadow mapping for the use in 2D scenes. In the canvas above you can test one of the two algorithms - shadow mapping. At first I implemented the two algorithms using C++ and OpenGL. Both make use of geometry shaders and layered depth maps for performant rendering. However, unfortunately neither of …