Fragment Shading Rate Handling for Lower GPU Memory Bandwidth

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing graphics processing systems face inefficiencies in handling variable fragment shading rates, leading to increased memory bandwidth and storage requirements, especially when combining different sources of fragment shading rate information.

Innovation Solution

A method and system for efficiently combining pipeline and primitive fragment shading rates by recognizing that consecutive primitives often share the same shading rate, allowing for calculation of combined rates only when a new rate is encountered, reducing the need for extensive storage and memory bandwidth.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If variable fragment shading rates are implemented by storing separate rate data for each primitive, then rendering flexibility and quality are improved, but memory bandwidth and storage requirements increase

Engineering Contradiction:
Improverendering flexibilityVSAvoidmemory bandwidth
Core Design Contradiction:
Adaptability or versatilityVSQuantity of substance

Solution Approach 1:

The patent combines multiple fragment shading rate values (pipeline level and primitive level) into a single combined fragment shading rate value. This merging approach allows the system to maintain rendering flexibility while reducing memory bandwidth requirements by eliminating the need to store and transfer separate rate data for each primitive.

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The combined fragment shading rate value serves multiple functions: it enables variable shading rates across different primitives, maintains compatibility with existing pipeline-level rate control, and reduces memory bandwidth consumption. This multi-functional approach allows a single data structure to achieve both flexibility and efficiency.

Inventive Principle:
Principle #6Universality (Multi-functionality)

2Manufacturing precision

If fragment shading rate data is stored for every primitive, then rendering precision is improved, but device complexity and storage requirements increase

Engineering Contradiction:
Improverendering precisionVSAvoidstorage requirements
Core Design Contradiction:
Manufacturing precisionVSDevice complexity

Solution Approach 1:

By merging pipeline-level and primitive-level fragment shading rate values into a single combined value, the patent reduces storage requirements while preserving the precision needed for variable shading rates. This eliminates redundant storage of separate rate data for each primitive.

Inventive Principle:
Principle #5Merging (Combining)

3Manufacturing precision

If separate fragment shading rate calculations are performed for each primitive, then rendering accuracy is improved, but processing time and computational overhead increase

Engineering Contradiction:
Improverendering accuracyVSAvoidprocessing time
Core Design Contradiction:
Manufacturing precisionVSLoss of time

Solution Approach 1:

The patent performs the fragment shading rate combination operation in advance during the geometry processing phase, before the rendering phase begins. This preliminary calculation allows the combined rate values to be stored and reused during rendering, eliminating the need for repeated calculations and reducing processing time during the actual rendering operation.

Inventive Principle:
Principle #10Preliminary action

4Adaptability or versatility

If extensive fragment shading rate data is stored for each primitive, then variable shading rate functionality is improved, but memory bandwidth consumption increases

Engineering Contradiction:
Improvevariable shading rate functionalityVSAvoidmemory bandwidth consumption
Core Design Contradiction:
Adaptability or versatilityVSQuantity of substance

Solution Approach 1:

The patent merges pipeline-level and primitive-level fragment shading rate values into combined values that are stored in a unified data structure. This merging reduces memory bandwidth consumption by eliminating redundant storage of separate rate data while preserving the full variable shading rate functionality needed for different rendering scenarios.

Inventive Principle:
Principle #5Merging (Combining)

Data Source

PatentUS12555301B2Graphics processing system and method of rendering
Publication Date: 2026.02.17 IMAGINATION TECH LTD
  • US12555301B2 patent drawing
  • US12555301B2 patent drawing
  • US12555301B2 patent drawing

AI summary

A method of rendering a scene formed by primitives in a graphics processing system. For a sequence of primitives, a pipeline fragment shading rate value and a primitive fragment shading rate value for a primitive are combined to produce a combined fragment shading rate value for the primitive. Fragment shading rate data representing the combined fragment shading rate value for the primitive is stored and data identifying the primitive is associated with the fragment shading rate data. For a subsequent primitive, it is determined whether or not a combined fragment shading rate value for the subsequent primitive is the same as for the preceding primitive. If it is the same, data identifying the subsequent primitive is associated with the fragment shading rate data that the data identifying the preceding primitive is associated with. If it is not the same, further fragment shading rate data representing the combined fragment shading rate value for the subsequent primitive is stored and data identifying the subsequent primitive is associated with the further fragment shading rate data.