Hybrid Digital Data Processing System With Interconnection Module

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current digital data processing systems for video signals, such as those used for temporal noise reduction and other operations like luminance/chrominance separation and deinterlacing, are cumbersome due to their reliance on iterative calculations and the use of buffer memories, and existing solutions whether purely hardware or software-based face inflexibility, high production costs, or complex design issues.

Innovation Solution

A digital data processing system comprising slave processing units, an interconnection module for data transfer, and a control unit that separates control and processing functions, utilizing programmable and non-programmable units with shared memory and DMA capabilities to efficiently transfer and process multimedia data, including video pixels, with features like unsolicited processing deactivation and multiplexing to optimize resource use.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If purely hardware solutions are used for video processing, then processing performance is improved, but device complexity and design difficulty increase

Engineering Contradiction:
Improveprocessing performanceVSAvoiddesign difficulty
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The system divides video processing into two distinct segments: a hardware acceleration unit for computationally intensive operations (motion detection, filtering calculations) and a software control unit for managing data flow and coordinating operations. This segmentation allows the hardware to handle performance-critical tasks while the software manages complexity, resolving the contradiction between processing performance and design difficulty.

Inventive Principle:
Principle #1Segmentation

2Adaptability or versatility

If purely software solutions are used for video processing, then flexibility and ease of implementation are improved, but processing speed and performance deteriorate

Engineering Contradiction:
ImproveflexibilityVSAvoidprocessing speed
Core Design Contradiction:
Adaptability or versatilityVSProductivity

Solution Approach 1:

The system merges software and hardware approaches into a hybrid architecture where the hardware acceleration unit provides fast processing for standard operations while the software control unit maintains flexibility for adapting to different processing requirements. This combination resolves the contradiction by achieving both high processing speed through hardware and flexibility through software control.

Inventive Principle:
Principle #5Merging (Combining)

3Productivity

If buffer memories are used for storing video data, then processing capability is improved, but device complexity and production cost increase

Engineering Contradiction:
Improveprocessing capabilityVSAvoiddevice complexity
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The system extracts the buffer memory requirement from the overall system architecture by implementing a streamlined data flow where data is processed in real-time streams with minimal buffering. The hardware acceleration unit processes data as it arrives, eliminating the need for large buffer memories while maintaining processing capability, thus resolving the contradiction between processing capability and device complexity.

Inventive Principle:
Principle #2Taking out (Extraction)

4Manufacturing precision

If iterative calculations are used for noise reduction and filtering, then processing quality is improved, but processing time and complexity increase

Engineering Contradiction:
Improveprocessing qualityVSAvoidprocessing time
Core Design Contradiction:
Manufacturing precisionVSLoss of time

Solution Approach 1:

The system performs preliminary action by pre-calculating filter coefficients and motion compensation parameters in advance, storing them in registers for rapid access during iterative processing. This preparation eliminates the need for time-consuming calculations during the actual noise reduction and filtering operations, maintaining high processing quality while significantly reducing processing time.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentEP2221727B1System and method for processing digital data
Publication Date: 2020.01.15 STMICROELECTRONICS (GRENOBLE 2) SAS
  • EP2221727B1 patent drawingFigure 1
  • EP2221727B1 patent drawingFigure 2
  • EP2221727B1 patent drawingFigure 3

AI summary

The system has slave processing units (14) for execution of elementary functions. An interconnection module (10) communicates with a data transfer network (SoC), and transfers data between the slave processing units and the network. A control unit (18) of the interconnection module controls transfer of data between the slave processing units and the network. The slave processing units are formed of non-programmable hardware processing units (14a-14d) and a programmable processing unit (16). A shared memory (20) is associated with the programmable processing unit. An independent claim is also included for a method for processing digital signals.