System Level Caches for Memory Copy in Mesh Networks
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In mesh networks, memory copy operations involve redundant traffic as data is copied to and from a central processing unit (CPU) for the purpose of performing the copy operation, which is inefficient.
Innovation Solution
Configuring system level caches to perform memory copy operations, allowing data to be written directly to a destination or another system level cache, thereby avoiding the need for data to be sent to and from the CPU.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If data is copied through a central processing unit (CPU) in a mesh network, then the copy operation can be performed, but redundant traffic is created since data must be sent to and from the CPU
Solution Approach 1:
The patent extracts the CPU from the memory copy operation by implementing system level caches that can perform copy operations independently. The caches are configured to handle read and write requests directly without involving the CPU, thereby eliminating redundant traffic while maintaining copy functionality.
Solution Approach 2:
The system level caches act as intermediaries between the source and destination memory locations. Instead of data traveling through the CPU, the caches mediate the copy operation by receiving read requests, storing data temporarily, and facilitating write requests to the destination, thus reducing redundant traffic.
2Device complexity
If a central processing unit (CPU) is used for memory copy operations, then copy control can be centralized, but network traffic increases due to data needing to be sent to and from the CPU
Solution Approach 1:
The patent segments the memory copy operation into independent read and write phases handled by system level caches. The caches are configured with separate read and write request handling mechanisms that operate independently, allowing copy control without requiring data to traverse through a central CPU, thus reducing network traffic.
Solution Approach 2:
The system level caches perform self-service by autonomously handling memory copy operations. The caches are configured to process read requests, store data locally, and facilitate write requests without requiring CPU intervention, thereby maintaining copy control functionality while significantly reducing network traffic.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Aspects of the disclosure are directed to configuring one or more system level caches to perform memory copy in a mesh network. The system level caches can perform a write to a write destination or perform a write to another system level cache that performs the write to the write destination. The system level caches allow for avoiding redundant traffic, as data no longer needs to be sent to and from a CPU when performing memory copy.