[video] Reducing Graphics API Complexity: A Clean Slate Design for Modern GPUs traces the evolution of graphics APIs from OpenGL to D3D12, Vulkan, and Metal highlights the complexity bottleneck of modern APIs, including driver overhead, pipeline state object (PSO) stuttering, and resource-heavy barriers proposes an alternative design utilizing a simple GPU memory model, pointer-based bindings, as…
A Texture Lookup Approach to Bézier Curve Evaluation on the GPU presents a texture-based method for evaluating Bezier curves by leveraging hardware samplers extends the idea beyond curves to surfaces, volumes, and related spline families compares accuracy and performance against shader-polynomial evaluation wayback-archive Understanding Light in Computer Graphics | Taha Torabpour conversation on…
How to Read Mathematics? - A study guide provides a guide on how to independently work through mathematical papers, textbooks, and lecture notes emphasizes that reading mathematics is a difficult skill that requires specific methods to learn effectively outlines actionable steps to build a solid foundation and identify underlying structures in mathematical texts wayback-archive Ray tracing massive…
Shipping Godot VR and Porting to PSVR2: A Partial Post Mortem a detailed write-up of a talk at Develop Brighton 2026 about Godot VR development discusses rebuilding major engine parts like the label system and render server to meet console performance needs details the challenges of porting Godot to PS5/PSVR2 wayback-archive Advanced Vulkan Compute: The Power of Parallelism an introductory guide…
Half-Edge Data Structure. Part 2 deep dive into the inner workings of the OpenMesh mesh creation logic explains the process of adding new faces to an existing mesh details the algorithm and optimizations used to maintain a valid topological graph wayback-archive PEPS: Positional Encoding Projected Sampling introduces Positional Encoding Projected Sampling (PEPS), a framework that treats coordinate…
Neural Render Proxies for Interactive and Differentiable Lighting introduces a scene-specific neural render proxy that enables differentiable relighting of static scenes decouples path sampling from emission computation by collecting light-agnostic transport samples and training a lightweight network to map them to pixel outputs allows scaling with resolution and light complexity rather than scene…
Multi-Layer Reservoir Splatting for Temporal Reuse under Disocclusion introduces a multi-layer ReSTIR variant that preserves sample history when occluded uses reservoir splatting and layered depth ranges to move samples between screen-space layers without tracing extra rays demonstrates much lower disocclusion noise for temporally reused samples with only a small extra performance cost…
Why does ASTC use ISE when almost nothing else does? explains why ASTC uses integer sequence encoding (ISE) shows that ISE’s advantage over a simple prefix code is only about 0.07 bits per symbol in practice argues the real benefit is that the predictability of fixed-size payloads simplifies encoder design wayback-archive Implicit Surface rendering for CAD describes a CAD prototype that renders…
Floor and Ceil Versus Denormals on CPU and GPU explores the behavior of floor and ceil functions when dealing with denormalized floats discusses how different platforms (CPU vs. GPU) handle denormals, with some flushing to zero and others preserving them provides an HLSL implementation for deterministic implementations that behave consistently across devices wayback-archive Dual Contouring of…
On Rendering the Sky, Sunsets, and Planets walks through a WebGPU-based atmospheric rendering system builds the shader step-by-step from raymarching through Rayleigh/Mie scattering, ozone absorption, and optical depth compares a full atmosphere shader against a faster LUT-based approximation for quality and performance wayback-archive Triangle Tessellation with Clamped Parallelograms revisits…
niagara: Opacity micromaps live demo expands the Vulkan implementation to support micromaps for ray-traced shadows explains the concept of micromaps and what MeshOptimizer supports followed by showing the full implementation integration process on the C++ and shader side Wave Tracing: Generalizing The Path Integral To Wave Optics – EUROGAPHICS 2026 Talk introduces a wave tracing framework that…
Writing a bindless GPU abstraction layer introduces Loon GPU, a bindless abstraction layer implemented on Vulkan 1.3 and Metal 4 exposes GPU allocations as device pointers, removes explicit vertex buffers, bind groups, and image layouts discusses Slang shader portability issues and the tradeoffs of simplifying the GPU API surface wayback-archive Revealing NVIDIA Closed-Source Driver Command…
Cooperative Vectors Introduction introduces Cooperative Vectors, a GPU API that enables hardware-accelerated vector–matrix multiplications inside shaders explains the motivation from neural material and neural radiance caching use cases covers practical inference using MulOptimal matrix layouts and training via OuterProductAccumulate and VectorAccumulate wayback-archive CuRast: Cuda-Based Software…
Modern rendering culling techniques covers the main culling techniques used in modern real-time renderers, grouped by category explains distance, backface, frustum, occlusion (Hi-Z, two-pass GPU-driven approaches), and meshlet-level cluster culling discusses how techniques work together and when to apply each one wayback-archive Multi-Threading & Mutation The author argues that the key to writing…
Introduction to Spherical Harmonics for Graphics Programmers introduces spherical harmonics as an orthonormal basis for approximating functions defined on a sphere, with a focus on lighting applications walks through the mathematical foundations with interactive in-browser examples for cubemap projection covers practical pitfalls wayback-archive Real-time Neural Six-way Lightmaps proposes a neural…