Tile Buffer Deferred Shading On-Chip Processing

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current graphics processing systems face significant bandwidth and power consumption issues during deferred shading operations, particularly in tile-based graphics processing pipelines, due to the need for frequent external memory reads and writes.

Innovation Solution

A method and system that includes a programmable processing stage within the graphics processing pipeline, allowing for the storage and processing of multiple render targets in a tile buffer, enabling deferred shading operations to be performed on-chip with zero external bandwidth cost by reading and writing data directly within the tile buffer.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If deferred shading operations are performed using conventional graphics processing pipelines, then the rendering quality and visual effects are improved, but bandwidth consumption and power usage increase significantly due to frequent external memory reads and writes

Engineering Contradiction:
Improverendering qualityVSAvoidpower consumption
Core Design Contradiction:
ReliabilityVSUse of energy by moving object

Solution Approach 1:

The patent divides the frame buffer into multiple tile buffers, each storing a portion of the render targets. This segmentation allows the programmable processing stage to access only the relevant tile buffer data locally, eliminating the need for frequent external memory transactions and reducing power consumption while maintaining rendering quality

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent introduces a new dimension of processing by enabling the programmable processing stage to directly read and write tile buffer data without external memory intervention. This dimensional change in the data access path eliminates bandwidth bottlenecks and reduces power usage associated with external memory transactions

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

2Reliability

If deferred shading operations are performed using conventional graphics processing pipelines, then the rendering quality and visual effects are improved, but bandwidth consumption and power usage increase significantly due to frequent external memory reads and writes

Engineering Contradiction:
Improverendering qualityVSAvoidbandwidth consumption
Core Design Contradiction:
ReliabilityVSProductivity

Solution Approach 1:

The patent divides the frame buffer into multiple tile buffers, each storing a portion of the render targets. This segmentation allows the programmable processing stage to access only the relevant tile buffer data locally, eliminating the need for frequent external memory transactions and reducing power consumption while maintaining rendering quality

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent introduces a new dimension of processing by enabling the programmable processing stage to directly read and write tile buffer data without external memory intervention. This dimensional change in the data access path eliminates bandwidth bottlenecks and reduces power usage associated with external memory transactions

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

3Loss of information

If multiple render targets are stored in external memory for deferred shading operations, then the completeness and accuracy of rendering data are improved, but the time and power required for data access increase

Engineering Contradiction:
Improverendering data completenessVSAvoiddata access time
Core Design Contradiction:
Loss of informationVSLoss of time

Solution Approach 1:

The patent divides the frame buffer into multiple tile buffers, each storing a portion of the render targets. This segmentation allows the programmable processing stage to access only the relevant tile buffer data locally, eliminating the need for frequent external memory transactions and reducing power consumption while maintaining rendering quality

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent performs preliminary actions by storing render target data in tile buffers before the deferred shading operations are executed. This pre-positioning of data in local memory eliminates the need for time-consuming external memory transactions during the actual processing, reducing data access time while maintaining data completeness

Inventive Principle:
Principle #10Preliminary action

4Loss of information

If multiple render targets are stored in external memory for deferred shading operations, then the completeness and accuracy of rendering data are improved, but the time and power required for data access increase

Engineering Contradiction:
Improverendering data completenessVSAvoidpower consumption
Core Design Contradiction:
Loss of informationVSUse of energy by moving object

Solution Approach 1:

The patent divides the frame buffer into multiple tile buffers, each storing a portion of the render targets. This segmentation allows the programmable processing stage to access only the relevant tile buffer data locally, eliminating the need for frequent external memory transactions and reducing power consumption while maintaining rendering quality

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent performs preliminary actions by storing render target data in tile buffers before the deferred shading operations are executed. This pre-positioning of data in local memory eliminates the need for time-consuming external memory transactions during the actual processing, reducing data access time while maintaining data completeness

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentUS9767595B2Graphics processing systems
Publication Date: 2017.09.19 ARM LTD
  • US9767595B2 patent drawing
  • US9767595B2 patent drawing
  • US9767595B2 patent drawing

AI summary

A tile-based graphics processing pipeline 1 comprising a rasteriser 3, a renderer 6, a tile buffer 10, a write out stage 13 and a programmable processing stage 14. The tile buffer 10 stores multiple render targets for a deferred shading operation and the programmable processing stage 14 is operable to, under the control of graphics program instructions, read data from two or more of a set of multiple render targets for a deferred shading operation stored in the tile buffer 10, perform a deferred shading processing operation using the read data, and to write the result of the processing operation to an output render target in the tile buffer 10, or to external memory.