Multi-Layer Video Decoding via Partitioned Core Assignment

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current video decoding technologies face inefficiencies in processing bitstreams with multiple layers, as they often rely on a single most capable hardware core, leaving less-capable cores idle, which can prolong decoding times and limit parallel processing capabilities.

Innovation Solution

The method involves decoding bitstreams by obtaining syntax elements indicating partitioning schemes that divide layers into disjoint partitions, allowing different processing cores to decode each partition independently, thereby utilizing multiple hardware cores in parallel.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If a single most capable hardware core is used to decode multi-layer bitstreams, then decoding reliability is improved, but decoding time increases and processing productivity decreases

Engineering Contradiction:
Improvedecoding reliabilityVSAvoiddecoding speed
Core Design Contradiction:
ReliabilityVSProductivity

Solution Approach 1:

The patent divides the multi-layer bitstream into multiple partitions, where each partition contains a subset of layers. Each partition is then decoded by a separate hardware core in parallel. This segmentation allows the system to utilize multiple cores simultaneously while maintaining decoding reliability through proper partition management and syntax element associations.

Inventive Principle:
Principle #1Segmentation

2Productivity

If multiple hardware cores are used for parallel decoding, then processing productivity is improved, but hardware complexity increases

Engineering Contradiction:
Improveparallel processing capabilityVSAvoidhardware core configuration
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The patent creates a universal decoding framework where multiple hardware cores can decode different partitions of the same multi-layer bitstream using the same decoding algorithms and processes. The syntax elements associated with each partition enable any core to handle any partition, providing multi-functionality without requiring specialized hardware for each core.

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

Solution Approach 2:

The system dynamically assigns different partitions to different hardware cores based on the partitioning scheme indicated in the bitstream. This dynamic allocation allows flexible utilization of available hardware resources without requiring fixed, dedicated hardware configurations for specific layer combinations.

Inventive Principle:
Principle #15Dynamics

3Ease of operation

If less-capable hardware cores are left idle, then decoding simplicity is maintained, but resource utilization efficiency decreases and decoding time increases

Engineering Contradiction:
Improvedecoding process simplicityVSAvoididle core time
Core Design Contradiction:
Ease of operationVSLoss of time

Solution Approach 1:

The bitstream is segmented into multiple partitions that can be distributed to different hardware cores. This segmentation ensures that each core, regardless of capability, has meaningful work assigned to it, eliminating idle time while maintaining the simplicity of using existing core configurations without requiring all cores to be equally capable.

Inventive Principle:
Principle #1Segmentation

Data Source

PatentEP3138292B1Method and device for encoding multi-layer video data including syntax elements associating profile, tier and level with partition containing one or more layers
Publication Date: 2019.09.18 QUALCOMM INC
  • EP3138292B1 patent drawingFigure 1
  • EP3138292B1 patent drawingFigure 2
  • EP3138292B1 patent drawingFigure 3

AI summary

A video decoder is configured to decode a bitstream that comprises an encoded representation of video data. As part of decoding the bitstream, the video decoder obtains, from the bitstream, one or more syntax elements indicating one or more partitioning schemes. For each respective partitioning scheme of the one or more partitioning schemes, the respective partitioning scheme specifies a respective set of disjoint partitions whose union forms an output layer set. Each respective partition of the respective set of disjoint partitions contains one or more of the layers. The video decoder is further configured to decode each of the partitions of a particular partitioning scheme using different processing cores in a plurality of hardware cores, the particular partitioning scheme being one of the one or more partitioning schemes.