Early Sample Evaluation for Small Primitives in Rasterization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional graphics processing pipelines often incorrectly identify small primitives as covering multiple pixel tiles, leading to unnecessary processing during fine rasterization, as they may only cover samples within one tile.
Innovation Solution
A method is introduced where a primitive is evaluated for per-sample coverage based on its bounding box dimensions. If no samples are covered, the primitive is discarded during coarse rasterization, and early sample evaluation is performed to correctly identify which fine raster tiles are covered by small primitives lying on tile boundaries.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If coarse rasterization identifies pixel tiles covered by a primitive using bounding box, then the coverage identification is simple and fast, but small primitives may be incorrectly identified as covering multiple pixel tiles leading to unnecessary fine rasterization processing
Solution Approach 1:
The patent performs preliminary sample coverage evaluation during coarse rasterization before committing to fine rasterization processing. By evaluating whether samples are actually covered by the primitive using the covering test, the system提前 identifies and discards primitives that don't cover any samples, preventing unnecessary fine rasterization work while maintaining accurate coverage identification
Solution Approach 2:
The patent applies different processing strategies based on the size and characteristics of primitives. For small primitives that may not cover entire pixels, the system performs detailed per-sample coverage evaluation rather than assuming full pixel coverage based on bounding box intersection, thereby improving accuracy for specific cases without affecting overall processing efficiency
2Reliability
If fine rasterization processes all pixel tiles identified by coarse rasterization, then all potentially covered areas are processed, but processing time is wasted on pixel tiles that contain no covered samples
Solution Approach 1:
The patent performs preliminary sample coverage evaluation during coarse rasterization before committing to fine rasterization processing. By evaluating whether samples are actually covered by the primitive using the covering test, the system提前 identifies and discards primitives that don't cover any samples, preventing unnecessary fine rasterization work while maintaining accurate coverage identification
Solution Approach 2:
The patent discards small primitives that are determined not to cover any samples during the coarse rasterization stage. This selective discarding eliminates wasted processing in the fine rasterization stage, improving overall efficiency without losing any visually relevant information since the discarded primitives contribute nothing to the final image
Data Source
AI summary
A technique for early sample evaluation during coarse rasterization of primitives reduces the number of pixel tiles that are processed during fine rasterization of the primitive. A primitive bounding box determines when a primitive is small and may not actually cover any samples within at least one fine raster tile. Early sample evaluation is performed for the small primitive during coarse rasterization and the small primitive is discarded when no samples are actually covered by the small primitive. When the small primitive lies on a boundary between at least two fine raster tiles, early sample evaluation is performed during coarse rasterization to correctly identify which, if any, of the at least two fine raster tiles includes samples that are actually covered by the small primitive.