Tile-Based Graphics Rendering With Integer-Multiple FDM Texels
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Tile-based graphics processing systems face challenges in implementing fragment density maps due to non-uniform sample positions and increased computational complexity, as they are optimized for a fixed native tile size and memory/buffer configurations.
Innovation Solution
Constrain FDM texel sizes to be integer multiples of the native tile size, allowing uniform fragment sizes within tiles while varying sampling densities across the frame, and utilize the parameter fetch unit to retrieve and distribute FDM information efficiently to the sampling unit.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If fragment density maps are implemented in tile-based graphics processing systems, then flexible fragment shading rates can be achieved, but processing complexity increases due to non-uniform sample positions
Solution Approach 1:
The patent changes the parameter of texel size to be an integer multiple of native tile size, which transforms the fragment density map structure to be compatible with tile-based rendering. This parameter change allows flexible shading rates while maintaining uniform processing within each tile, reducing the complexity caused by non-uniform sample positions.
Solution Approach 2:
The patent segments the rendering frame into tiles, where each tile corresponds to an integer multiple of a native tile size. This segmentation ensures that within each tile, fragment sampling is uniform and manageable, while the overall frame can still have variable shading rates across different regions through the fragment density map.
2Manufacturing precision
If fragment density maps with varying sampling densities are used, then rendering quality can be optimized, but computational load increases
Solution Approach 1:
The patent applies local quality by allowing different fragment sampling densities in different regions of the frame through the fragment density map. Each tile can have its own sampling density based on the texel size, enabling high rendering quality in important areas while using lower sampling rates in less critical areas, thus optimizing the balance between quality and computational load.
3Adaptability or versatility
If non-integer multiple texel sizes are used in FDM, then flexible sampling densities are achieved, but tile-based operations become inconsistent
Solution Approach 1:
The patent changes the parameter constraint by requiring texel sizes to be integer multiples of native tile sizes. This parameter change ensures that tile-based operations remain consistent and predictable, while still allowing flexibility in sampling densities by choosing different integer multiples for different regions of the frame.
Data Source
AI summary
A method of rendering a frame showing a scene formed by primitives in a tile-based graphics processing system includes a geometry processing phase tiling the primitives in the scene, to determine which primitives at least partially overlap which tiles of the frame to be rendered. A rendering phase obtains a fragment density map defining one or more texels, each texel corresponding to an area of the frame to be rendered and having an associated fragment size, wherein for each of the texels, the texel's height is an integer multiple of a native tile height used in the tile-based graphics processing system and the texel's width is an integer multiple of a native tile width used in the tile-based graphics processing system. The rendering phase also determines from the fragment density map a fragment size to be used to render the tile, performing sampling using the determined fragment size and performing fragment shading using the determined fragment size.