Reflective Memory Network Address Segmentation for Multi-Vendor Integration

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Reflective memory networks fail to maintain address uniqueness across different computing devices from different manufacturers, leading to data corruption when connected, as existing methods do not account for hardware and software differences between devices from manufacturers like Speedgoat and National Instruments.

Innovation Solution

Configuring the reflective memory network by defining specific rules and scripts that create contiguous address sets for each device, using 'ghost partitions' to reserve addresses for future use and avoid clashes, ensuring that each device writes to a dedicated set of addresses, and using a memory map to organize parameters in a sequential and non-overlapping manner.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If conventional memory mapping methods are used without accounting for manufacturer differences, then device compatibility and ease of integration are improved, but data integrity and reliability deteriorate due to address conflicts and corruption

Engineering Contradiction:
Improvedevice compatibilityVSAvoiddata integrity
Core Design Contradiction:
Adaptability or versatilityVSReliability

Solution Approach 1:

The reflective memory address space is segmented into distinct address ranges, with each computing device assigned a unique manufacturer-specific address range. This segmentation prevents address conflicts by ensuring that each device writes to and reads from its own dedicated address space, eliminating data corruption while maintaining multi-vendor compatibility

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

Different address mapping rules are applied locally to each computing device based on its manufacturer. Each device type (Speedgoat, National Instruments, etc.) has its own specific address assignment strategy, allowing the system to accommodate hardware and software differences between vendors while maintaining overall system reliability

Inventive Principle:
Principle #3Local quality

2Device complexity

If address spaces are allocated without manufacturer-specific considerations, then system complexity is reduced and ease of operation is improved, but measurement precision and address uniqueness deteriorate

Engineering Contradiction:
Improveconfiguration complexityVSAvoidaddress uniqueness
Core Design Contradiction:
Device complexityVSMeasurement precision

Solution Approach 1:

The address mapping parameters are changed based on the manufacturer of each computing device. Each vendor's devices use specific address ranges and allocation patterns tailored to their hardware architecture, ensuring unique address assignment while providing clear guidelines that reduce configuration complexity

Inventive Principle:
Principle #35Parameter changes

3Ease of manufacture

If generic address allocation is used across all devices, then ease of manufacture and integration are improved, but the risk of data corruption and network failure increases

Engineering Contradiction:
Improveintegration easeVSAvoiddata corruption risk
Core Design Contradiction:
Ease of manufactureVSObject-affected harmful factors

Solution Approach 1:

The patent applies preliminary anti-action by pre-defining manufacturer-specific address ranges before devices are integrated into the network. This preventive measure eliminates the possibility of address conflicts and data corruption by ensuring that each device has its own protected address space from the outset, rather than attempting to resolve conflicts after they occur

Inventive Principle:
Principle #9Preliminary anti-action

Data Source

PatentEP3531293A1Computing system operating a reflective memory network
Publication Date: 2019.08.28 BAE SYSTEMS PLC
  • EP3531293A1 patent drawingFigure 1
  • EP3531293A1 patent drawingFigure 2A
  • EP3531293A1 patent drawingFigure 2A

AI summary

A computing system (100) comprises a plurality of computing devices (102) configured to collectively operate a reflective memory network. Each of the computing devices is configured to execute a respective part (109) of an application set that processes a plurality of parameters. The reflective memory network is configured as a series of sets of contiguous addresses, each of the sets associated with a respective one of the plurality of computing devices and including a predefined number of the contiguous addresses useable only for storing the at least one parameter written by the part of the application set executed by the associated computing device.