Video Scaling via Multiple Paths for Power Efficiency
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing video scalers struggle to meet performance specifications for real-time scaling of video data between different formats and higher resolution formats, leading to inefficiencies and increased power consumption when handling higher pixel throughput.
Innovation Solution
A method and apparatus that utilize multiple video paths to scale a frame of video data by partitioning it into portions, processing each portion separately with two-dimensional video scalers, and combining the scaled pixels to achieve arbitrary scaling ratios, reducing the operational frequency and power requirements while maintaining performance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If a single video scaler is used to process high-resolution video data, then the scaling function is simple, but the processing speed and performance specifications are insufficient
Solution Approach 1:
The patent divides the video processing task into multiple parallel paths, each handling a portion of the video data. Multiple video scalers process different segments simultaneously, increasing overall processing throughput while keeping each individual scaler's complexity manageable.
Solution Approach 2:
The patent combines multiple scaled video portions through a compositor to produce the final scaled video output. This merging approach allows parallel processing of video segments while maintaining a unified output stream, achieving high processing speed without requiring a single complex scaler.
2Productivity
If the video scaler operates at higher clock rates to meet performance specifications, then the processing capability increases, but the power consumption increases
Solution Approach 1:
By segmenting the video processing workload across multiple parallel paths, each scaler can operate at lower clock rates while collectively achieving the required processing throughput. This reduces power consumption compared to a single scaler operating at high frequency.
Solution Approach 2:
The patent uses multiple video paths that may process slightly more data than strictly necessary (excessive action), allowing each path to operate at reduced speed while the aggregate throughput meets performance requirements, thereby reducing overall power consumption.
3Productivity
If existing video scalers are used for high-resolution formats, then the device architecture is simple, but they cannot meet the performance specifications for real-time scaling
Solution Approach 1:
The patent segments the video data into multiple portions that can be processed in parallel by separate video scalers. This segmentation enables real-time processing of high-resolution video by distributing the computational load, overcoming the limitations of existing single-scaler architectures.
Solution Approach 2:
The patent creates a multi-functional video processing architecture where multiple video scalers and a compositor work together as an integrated system. This universal architecture can handle various high-resolution formats while meeting real-time performance specifications, replacing the need for format-specific single-scaler designs.
Data Source
AI summary
A video scaling technique includes scaling a first dimension and a second dimension of a frame of video data to generate a scaled frame of video data. The scaling includes scaling the second dimension of a first portion of a frame of video data at a first rate to generate first scaled pixels and scaling the second dimension of a second portion of the frame of video data at the first rate to generate second scaled pixels. The scaling includes combining first output pixels based on the first scaled pixels and second output pixels based on the second scaled pixels to provide pixels of the scaled frame of video data at a second rate. The first rate is a fraction of the second rate.