Video Pipeline Interleaving for Multi-Display GPU Cost Reduction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current graphics processing unit (GPU) architectures are limited in supporting multiple display devices without the need for additional video pipelines, leading to increased cost and power consumption when trying to drive more than two display devices.
Innovation Solution
A horizontal scaling filter is integrated into a video pipeline to process video data by interleaving pixels from multiple images, allowing a single GPU with two independent video pipelines to support multiple display devices efficiently, using storage elements, multipliers, and a summation unit to generate weighted pixel data for output.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If additional independent video pipelines are included within the GPU to drive additional display devices, then the number of display devices that can be attached is increased, but the cost and complexity of the GPU increases
Solution Approach 1:
The patent divides the video pipeline into multiple sub-pipelines that can be independently configured. Each sub-pipeline can be assigned to drive a different display device, allowing a single GPU to support more than two display devices by segmenting the processing workload across multiple sub-pipelines within the existing pipeline architecture.
Solution Approach 2:
The patent implements dynamic configuration of video pipelines where sub-pipelines can be dynamically assigned, unassigned, or shared based on the number and requirements of connected display devices. This dynamic allocation allows the GPU to adapt to different display configurations without requiring permanent additional hardware pipelines.
2Adaptability or versatility
If additional GPUs are configured to drive additional display devices, then the number of display devices is increased, but the power consumption and cost increase
Solution Approach 1:
The patent makes the video pipeline subsystem universal by enabling it to serve multiple display devices through shared sub-pipelines. Instead of requiring dedicated pipelines for each display device, the same pipeline infrastructure can be dynamically allocated to different displays, reducing the total number of active processing units and thereby lowering power consumption.
Solution Approach 2:
The patent merges the functionality of multiple independent video pipelines into a single pipeline system with shared sub-pipelines. By combining the processing tasks for multiple display devices into one unified pipeline architecture, the system reduces redundant hardware and lowers overall power consumption compared to using separate GPUs.
3Productivity
If a single video pipeline processes interleaved pixels from multiple images, then processing efficiency is improved, but the complexity of pixel processing increases
Solution Approach 1:
The patent performs preliminary interleaving of pixels from multiple images before they enter the video pipeline processing stages. By pre-organizing the pixel data into an interleaved format, the subsequent processing operations can handle multiple images more efficiently through a single pipeline, improving productivity while managing complexity through upfront data organization.
Data Source
AI summary
One embodiment of the present invention sets forth a system for generating multiple video output signals from a single video pipeline within a graphics processing unit. Pixel data from more than one display surface is retrieved and multiplexed before being transmitted to a video pipeline for processing. The resulting video pixel data is routed to video output encoders, which selectively accept the video pixel data for transmission to attached display devices.