Multi-Rate Shading Monolithic Program Mapping

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current graphics architectures struggle to efficiently vary shading rates across different regions of a screen, leading to increased power consumption and reduced image quality, especially in high-resolution displays and handheld devices, due to their inability to decouple shading and visibility sampling rates.

Innovation Solution

The implementation of coarse pixel shading (CPS) and multi-rate shading, which allows for flexible control of shading rates by decoupling shading and visibility sampling, using a monolithic program that executes at different rates per group of pixels, samples, and samples, with a new assembly instruction for fast switching between coarse-rate and pixel-rate execution, and a fixed-function accelerator for managing coarse-to-pixel mapping.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If per-pixel or per-sample shading is used to maintain image quality, then shading detail is preserved, but power consumption increases significantly

Engineering Contradiction:
Improveshading detailVSAvoidpower consumption
Core Design Contradiction:
Measurement precisionVSUse of energy by moving object

Solution Approach 1:

The patent segments the screen into multiple regions with different shading rates, allowing per-region optimization. Some regions use high shading rates for detail preservation while others use lower rates for power savings, resolving the contradiction between image quality and power consumption.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

Different regions of the screen are assigned different shading qualities based on their importance. Critical regions maintain per-pixel shading for high quality, while less critical regions use coarser shading rates, achieving local optimization of the power-quality tradeoff.

Inventive Principle:
Principle #3Local quality

2Use of energy by moving object

If frame buffer resolution is varied to control shading rates, then power consumption is reduced, but fine-grained variation of shading rates is lost

Engineering Contradiction:
Improvepower consumptionVSAvoidshading rate variation
Core Design Contradiction:
Use of energy by moving objectVSAdaptability or versatility

Solution Approach 1:

The patent introduces dynamic, fine-grained control of shading rates that can be adjusted independently for different regions and objects. This dynamic control mechanism allows the system to adapt shading rates in real-time based on scene requirements, overcoming the static nature of frame buffer resolution scaling.

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The patent adds a new dimension of control by introducing per-object and per-region shading rate parameters independent of the overall frame buffer resolution. This additional degree of freedom enables fine-grained variation without being constrained by global resolution changes.

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

3Use of energy by moving object

If coarse pixel shading is implemented to reduce power consumption, then energy efficiency improves, but hardware complexity increases

Engineering Contradiction:
Improvepower consumptionVSAvoidhardware complexity
Core Design Contradiction:
Use of energy by moving objectVSDevice complexity

Solution Approach 1:

The patent merges coarse pixel shading and fine pixel shading operations into a unified rendering pipeline. By integrating both shading modes and allowing them to work together, the system achieves power efficiency through coarse shading while maintaining image quality through fine shading where needed, without requiring completely separate hardware paths.

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The rendering hardware is designed to perform multiple shading functions using the same core infrastructure. The same pixel shader units can operate at different rates and modes, providing universal functionality that reduces overall hardware complexity compared to having dedicated separate paths for coarse and fine shading.

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

4Productivity

If multiple shading phases are implemented for different rates, then shading efficiency improves, but software overhead increases

Engineering Contradiction:
Improveshading efficiencyVSAvoidsoftware overhead
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The patent performs preliminary determination of which regions and objects require high-rate vs. low-rate shading before the actual rendering process. This advance planning allows the rendering pipeline to be configured optimally from the start, avoiding runtime overhead and complex switching logic during shader execution.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentUS9905046B2Mapping multi-rate shading to monolithic programs
Publication Date: 2018.02.27 INTEL CORP
  • US9905046B2 patent drawing
  • US9905046B2 patent drawing
  • US9905046B2 patent drawing

AI summary

In multi-rate shading, a coarse-rate shading phase is added on top of existing pixel-rate phase to significantly improve performance with minimum impact to image quality. Two shading phases evaluated at different rates may be mapped to one monolithic program running on processor graphics single instruction multiple data (SIMD) engines. In one embodiment, multi-rate shading allows a single rendering pass to execute shading code at one or more different rates: per group of pixels, per pixel, and per sample.