Content Addressable Memory Rule Sharing via Bit Masking
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing network units face inefficiencies in storing and applying rules due to excessive space and power consumption in content addressable memories (CAMs) when rules are relevant to multiple ports or network entities, leading to redundant storage and increased bandwidth usage.
Innovation Solution
The use of a bit mask to identify applicable entities, prepended to the rule in the CAM, allowing a rule to be stored once and applied selectively across multiple ports or entities by supplying a comparison mask during searches to enable or disable matching columns.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If a rule is stored once for each port to which it must be applied in traditional CAM organization, then the rule can be applied to multiple ports, but excessive space and power consumption are required in the CAM
Solution Approach 1:
The patent segments the rule storage structure into two parts: a shared rule definition and a port-specific matching field. The rule is stored once in the CAM with a port identifier field that can be selectively masked during matching operations. This allows the same rule to be applied to multiple ports without duplicating the entire rule entry in the CAM, thereby reducing power consumption while maintaining multi-port applicability.
Solution Approach 2:
The patent creates a universal rule storage structure where a single CAM entry can serve multiple ports through the use of a port identifier field that can be masked. The CAM is designed to accept wildcard or masked port identifiers, allowing one rule entry to function for multiple ports simultaneously. This multi-functional approach eliminates the need for separate rule copies for each port, reducing overall CAM usage and power consumption.
2Adaptability or versatility
If a rule is stored once for each port to which it must be applied in traditional CAM organization, then the rule can be applied to multiple ports, but valuable CAM storage space is consumed
Solution Approach 1:
The patent segments the rule storage structure into a shared rule definition and a port identifier field. The rule portion is stored once and shared across multiple ports, while only the port identifier needs to be replicated or masked for each port instance. This segmentation dramatically reduces the storage space required in the CAM compared to storing complete rule copies for each port.
Solution Approach 2:
The patent merges multiple port-specific rule instances into a single shared rule entry by combining the common rule definition with a port identifier field. This consolidation allows the CAM to store one rule entry that represents multiple port-specific rules, thereby reducing the total quantity of stored data while maintaining the ability to apply rules to multiple ports.
3Adaptability or versatility
If a rule is stored once for each port to which it must be applied in traditional CAM organization, then the rule can be applied to multiple ports, but maintenance of the rule requires accesses to multiple CAM locations increasing bandwidth usage
Solution Approach 1:
The patent segments the rule maintenance operation into a single centralized update of the shared rule definition rather than multiple distributed updates. When a rule needs to be modified, the change is made in one location in the CAM, and the modification automatically applies to all ports that use this rule. This eliminates the need to access multiple CAM locations for rule maintenance, reducing bandwidth usage.
Solution Approach 2:
The patent merges multiple rule maintenance operations into a single operation by consolidating the rule storage structure. Instead of updating separate rule copies in multiple CAM locations, the system performs one update on the shared rule entry, which then propagates to all relevant port instances. This merging of maintenance operations significantly reduces the bandwidth required for rule updates.
Data Source
AI summary
A content addressable memory stores entries each comprising a rule and as part of the entry a mask identifying all the entities to which the rule is applicable. A search pattern of data and a bit mask identifying the actual entity (or entities) associated with the data is applied as a search word along with a comparison mask that excludes all the other entities from the comparison of the search word with the entry. The CAM can thereby store efficiently in a single entry a rule that may be applicable to some but not all of a multiplicity of entities such as possible ingress ports of a network unit.