Logical Search Circuit Resource Division for Forwarding Performance
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current data search technologies in forwarding devices face limitations in search performance and entry specification due to constraints in memory access data bit width and logical resources, especially when handling multiple table lookup requests simultaneously.
Innovation Solution
A data search apparatus and method that utilizes a logical search circuit connected to a memory through a databus, allowing for dual or multi-forwarding modes without requiring additional bus or logical resources. This is achieved by dividing the logical search resource into parts, enabling each part to access node data through the bus resource, thus supporting simultaneous table lookup requests without increasing resource requirements.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If additional bus resources of memory access data bit width are added to implement dual forwarding mode, then search performance is improved, but device complexity and resource requirements increase
Solution Approach 1:
The single node logic is designed to perform multiple functions by sequentially handling different table lookup requests. The same node logic can process first table lookup requests, second table lookup requests, and third table lookup requests by switching between different memory blocks, eliminating the need for dedicated logic units for each forwarding mode.
Solution Approach 2:
The system dynamically switches between different memory blocks (first memory block, second memory block, third memory block) based on the type of table lookup request. This dynamic memory block selection allows a single node logic to adaptively handle different forwarding modes without requiring static additional resources.
2Productivity
If additional logical resources are added to implement dual forwarding mode, then search performance is improved, but device complexity and resource requirements increase
Solution Approach 1:
The single node logic serves multiple purposes by handling different types of table lookup requests sequentially. It can perform exact match table lookups, longest prefix match table lookups, and other search operations by switching between different memory blocks, replacing the need for multiple dedicated logical resources.
Solution Approach 2:
The node logic dynamically reconfigures its operation based on the incoming request type. When receiving a first table lookup request, it accesses the first memory block; when receiving a second table lookup request, it accesses the second memory block, enabling flexible resource utilization without additional logical resources.
3Productivity
If different memory modules are used to store same content to support simultaneous table lookup requests, then search performance is improved, but resource requirements and device complexity increase
Solution Approach 1:
The memory system is segmented into multiple memory blocks (first memory block, second memory block, third memory block), each storing different types of table data. This segmentation allows efficient organization of data for different search operations while being accessed through a unified interface by a single node logic.
Solution Approach 2:
A single node logic is designed to universally access all memory blocks through the databus. This universal access capability allows the same logical resource to efficiently handle different types of table lookup requests without requiring duplicate logical resources for each memory block.
4Adaptability or versatility
If memory access data bit width is increased to support larger entry specification, then entry specification is improved, but device complexity and resource requirements increase
Solution Approach 1:
Instead of increasing the data bit width in the horizontal dimension, the system adds a vertical dimension by introducing multiple memory blocks. This allows the system to handle larger entry specifications by accessing different memory blocks sequentially through the existing databus, rather than expanding the bus width.
Solution Approach 2:
The system dynamically switches between different memory blocks based on the search requirements, allowing flexible adaptation to different entry specifications without requiring a fixed increase in data bit width. The single node logic adapts its access pattern to match the required entry specification.
Data Source
AI summary
A data search apparatus includes a logical search circuit and a memory, and the logical search circuit is connected to the memory through a databus. The databus can access all memory resources, and each part of databus resource can access all the memory resources. A logical search resource provided by the logical search circuit can be divided into a plurality of parts as required, and each part of logical resource can access node data in the memory through the bus resource.