Unified Early Depth Test Unit for Reducing Memory Access in 3D Graphics

Solution Overview

Problem

Current graphic systems face inefficiencies in rendering 3D graphics due to high memory access requirements, particularly in determining pixel visibility, which leads to increased power consumption and latency.

Innovation Solution

A graphic processor with a unified early depth test (UEZT) unit that processes vertex data to generate fragment data based on depth values and mask bits, allowing for early determination of pixel visibility by comparing depth values against tile maximum and minimum values, reducing the need for external memory access.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If traditional rendering procedures are used to determine pixel visibility, then accurate visibility determination is achieved, but memory access requirements increase significantly

Engineering Contradiction:

Improvepixel visibility determination accuracyVSAvoidmemory access power consumption

Core Design Contradiction:

Measurement precisionVSUse of energy by moving object

Solution Approach 1:

The patent performs preliminary depth value comparisons against tile maximum and minimum values before conducting full rendering operations. By pre-categorizing pixels as definitely visible, definitely occluded, or uncertain based on depth value ranges, the system avoids unnecessary memory accesses for pixels that will not be rendered, thereby reducing power consumption while maintaining visibility determination accuracy

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent segments the depth value range into three distinct categories: pixels with depth values less than the tile minimum (definitely visible), pixels with depth values greater than the tile maximum (definitely occluded), and pixels with depth values between the minimum and maximum (uncertain). This segmentation allows the system to process only the uncertain pixels requiring full rendering and memory access, significantly reducing overall memory access requirements

Inventive Principle:

Principle #1Segmentation

2Measurement precision

If traditional rendering procedures are used to determine pixel visibility, then accurate visibility determination is achieved, but rendering latency increases

Engineering Contradiction:

Improvepixel visibility determination accuracyVSAvoidrendering latency

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The patent performs preliminary depth value comparisons against tile maximum and minimum values before conducting full rendering operations. By pre-categorizing pixels as definitely visible, definitely occluded, or uncertain based on depth value ranges, the system avoids unnecessary memory accesses for pixels that will not be rendered, thereby reducing power consumption while maintaining visibility determination accuracy

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent segments the depth value range into three distinct categories: pixels with depth values less than the tile minimum (definitely visible), pixels with depth values greater than the tile maximum (definitely occluded), and pixels with depth values between the minimum and maximum (uncertain). This segmentation allows the system to process only the uncertain pixels requiring full rendering and memory access, significantly reducing overall memory access requirements

Inventive Principle:

Principle #1Segmentation

3Measurement precision

If depth values of all pixels are compared with tile maximum and minimum values, then pixel visibility is accurately determined, but processing complexity increases

Engineering Contradiction:

Improvepixel visibility determination accuracyVSAvoidprocessing logic complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The patent segments the depth value range into three distinct categories: pixels with depth values less than the tile minimum (definitely visible), pixels with depth values greater than the tile maximum (definitely occluded), and pixels with depth values between the minimum and maximum (uncertain). This segmentation allows the system to process only the uncertain pixels requiring full rendering and memory access, significantly reducing overall memory access requirements

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent implements a unified early depth test mechanism that serves multiple functions: it performs preliminary visibility culling, generates classification masks for different pixel types, and identifies candidates for further rendering processing. This multi-functional approach consolidates what would otherwise require separate processing stages into a single integrated operation, managing complexity while maintaining accuracy

Inventive Principle:

Principle #6Universality (Multi-functionality)

Data Source

PatentUS9092906B2Graphic processor and method of early testing visibility of pixels

Publication Date: 2015.07.28 SAMSUNG ELECTRONICS CO LTD

AI summary

A graphic processor includes a rasterizer configured to process vertex data to generate fragment data based on a maximum depth value, a minimum depth value, and a mask bit of each pixel included in one tile, each mask bit indicating whether each pixel is drawn or not, the vertex data including three dimensional information of the pixels, a pixel shader configured to process the fragment data to generate color data, and a raster operation unit configured to convert the color data to pixel data to be displayed.