Multiple Machine Memory Update Overhead Reduction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The existing multiple computer architecture experiences substantial overhead in updating memory locations across interconnected computers, leading to inefficiencies due to the need to update all computers whenever any change is made, which can result in the use of stale data and increased network traffic.
Innovation Solution
Maintaining a record of which memory locations are present on which computers and only updating those specific locations, thereby reducing the volume of updating instructions passing over the communications network by ensuring only necessary updates are propagated.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If all memory locations are updated across all computers whenever any change is made, then data consistency is maintained, but network traffic and system overhead increase substantially
Solution Approach 1:
The patent applies local quality by differentiating between memory locations based on their accessibility patterns. Instead of uniformly updating all memory locations across all computers, the system identifies and updates only those memory locations that are actually accessed by the changed computer. This creates non-uniform update behavior where each computer selectively synchronizes only the specific memory locations relevant to its operations, thereby reducing overall network traffic while maintaining data consistency where needed.
2Reliability
If all memory locations are updated across all computers whenever any change is made, then data consistency is maintained, but computing speed decreases due to overhead
Solution Approach 1:
The patent segments the memory space into different categories based on accessibility patterns. It divides memory locations into those that are locally accessible versus those that require synchronization. By segmenting the update process in this way, the system can maintain data consistency for critical shared memory locations while avoiding unnecessary updates for locally-accessible memory, thereby reducing overhead and improving computing speed.
Solution Approach 2:
The system applies local quality by treating different memory locations differently based on their access characteristics. Memory locations are prioritized for updates based on which computers actually access them, creating a non-uniform synchronization strategy that improves overall system performance by avoiding unnecessary communication overhead.
3Reliability
If memory locations are replicated on all computers, then data consistency can be maintained, but the volume of data to be transmitted and updated increases
Solution Approach 1:
The patent applies partial action by updating only the subset of memory locations that are actually needed, rather than updating all replicated memory locations. This partial update approach reduces the volume of data transmitted across the network while still maintaining data consistency for the critical portions of memory that are shared between computers.
Data Source
AI summary
A multiple computer environment is disclosed in which an application program executes simultaneously on a plurality of computers (M1, M2, . . . Mn) interconnected by a communications network and in which the local memory of each computer is not maintained substantially the same by updating in due course. An address table mechanism is provided to permit access to an asset, object, or structure (i.e., memory location) for the purpose of updating, for example. Not all computers have the same memory, so it is not necessary for all computers to be updated.