GPU Command Stream Interleaving for Reduced Rendering Load

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Graphics processing units (GPUs) face increased computational loads when rendering high-resolution images at high frequencies, leading to reduced capability in performing other graphics or numerical computations.

Innovation Solution

A method is implemented to configure a graphics rendering command stream for reduced frame rendering, where frames are rendered at complementary reduced resolutions and then upscaled to nominal resolutions, lowering the computational load while maintaining image quality.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Manufacturing precision

If graphics rendering is performed at high resolution and high frequency, then image quality and display smoothness are improved, but computational load on GPU increases

Engineering Contradiction:
Improveimage qualityVSAvoidcomputational load
Core Design Contradiction:
Manufacturing precisionVSPower

Solution Approach 1:

The patent divides the rendering process into two separate passes: a coarse rendering pass that processes only dynamically changing elements (objects, lights, shadows) at reduced resolution, and a fine rendering pass that processes static background elements at full resolution. This segmentation allows the system to maintain high image quality for static elements while reducing computational load for dynamic elements, resolving the contradiction between image quality and computational load.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent applies different rendering qualities to different regions of the display: static background regions are rendered at full resolution, while dynamic foreground regions are rendered at reduced resolution and then superimposed. This local quality approach ensures that areas requiring high detail (static backgrounds) receive full resolution processing, while areas with motion (dynamic objects) use reduced resolution processing, thereby maintaining overall image quality while reducing total computational load.

Inventive Principle:
Principle #3Local quality

2Productivity

If GPU processes more frames per second, then display frequency is improved, but capability to perform other computations decreases

Engineering Contradiction:
Improvedisplay frequencyVSAvoidcomputational capability
Core Design Contradiction:
ProductivityVSAdaptability or versatility

Solution Approach 1:

The patent implements partial action by rendering only the necessary portions of each frame at full resolution. Specifically, static background elements are rendered once at full resolution and reused across multiple frames, while only dynamic elements are re-rendered at reduced resolution for each frame. This partial rendering approach maintains high display frequency while freeing GPU resources for other computational tasks.

Inventive Principle:
Principle #16Partial or excessive action

Solution Approach 2:

The patent performs preliminary rendering of static background elements in advance, storing them for reuse across multiple frames. This preliminary action allows the GPU to avoid re-processing static elements in subsequent frames, thereby reducing the computational load per frame and enabling higher display frequencies while maintaining capability for other computations.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentUS8947432B2Accelerated rendering with temporally interleaved details
Publication Date: 2015.02.03 NVIDIA CORP
  • US8947432B2 patent drawing
  • US8947432B2 patent drawing
  • US8947432B2 patent drawing

AI summary

One embodiment of the invention sets forth a mechanism for interleaving consecutive display frames rendered at complementary reduced resolutions. The GPU driver configures a command stream associated with a frame received from a graphics application for reduced frame rendering. The command stream specifies a nominal resolution at which the frame should be rendered. The reduced resolution associated with the frame is determined based on the reduced resolution of an immediately preceding frame (i.e., the complementary reduced resolution), if one exists, or on GPU configuration information. The GPU driver then modifies the command stream to specify the reduced resolution. The GPU driver also inserts an upscale command sequence specifying the nominal resolution into the command stream. Once the command stream is configured in such a manner, the GPU driver transmits the command stream to the GPU for reduced rendering.