Parallel Longest Prefix Matching Across Interspersed Search Spaces
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Packet switching systems face challenges in efficiently processing packets due to the limitations of longest prefix matching operations, particularly in handling varying prefix lengths across multiple search spaces, which affects scalability and resource utilization.
Innovation Solution
The implementation of a method that performs longest prefix matching operations in multiple interspersed prefix length search spaces using two or more lookup units, where the overall longest matching result is determined by comparing the prefix lengths from each search space, allowing for improved scalability by distributing the operations across different hardware modules.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If longest prefix matching operations are performed in a single search space, then the lookup operation is simple, but the system cannot handle varying prefix lengths across multiple search spaces and lacks scalability
Solution Approach 1:
The patent divides the routing table into multiple search spaces (first search space and second search space), each storing prefixes with specific length characteristics. This segmentation allows the system to handle varying prefix lengths efficiently while maintaining manageable complexity in each individual search space.
Solution Approach 2:
The patent introduces an additional dimension to the lookup operation by performing parallel longest prefix matching operations across multiple search spaces. Instead of a single-dimensional search, the system searches across multiple dimensions (search spaces) and selects the best match, enabling handling of varying prefix lengths without proportionally increasing complexity.
2Productivity
If multiple search spaces are used to store prefixes of varying lengths, then the system becomes more scalable, but the complexity of determining the overall longest matching prefix increases
Solution Approach 1:
The patent performs preliminary longest prefix matching operations in parallel across multiple search spaces before selecting the overall best match. By pre-computing the longest matching prefix in each search space independently, the system avoids the complexity of evaluating all possible combinations across search spaces, thus improving lookup speed while controlling operation complexity.
Solution Approach 2:
The patent creates copies of the lookup value and performs identical longest prefix matching operations in parallel across multiple search spaces. This copying approach allows independent evaluation of each search space without increasing the fundamental operation complexity, as each copy undergoes the same standardized matching process.
3Productivity
If parallel lookup operations are performed across multiple search spaces, then resource utilization is improved, but the coordination and comparison of results from different search spaces becomes more complex
Solution Approach 1:
The patent replaces complex coordination mechanisms with a straightforward comparison operation. Instead of requiring sophisticated protocols to coordinate results from parallel lookup operations, the system simply compares the prefix lengths from each search space and selects the longest match. This substitution of a simple comparison mechanism for complex coordination improves processing efficiency while maintaining ease of operation.
Data Source
AI summary
In one embodiment, longest prefix matching (LPM) operations are performed on a value in multiple interspersed prefix length search spaces to determine an overall longest prefix matching result in a packet switching system. A first LPM lookup unit performs a first LPM operation on the particular lookup value in a first search space finding a first longest matching prefix, and a second LPM lookup unit performs a second LPM operation on the particular lookup value in a second search space finding a second longest matching prefix. The longer of the first and second longest matching prefixes determines the overall LPM. In one embodiment, the first search space and the second search space include non-default route prefixes with interspersed prefix lengths matching a same value, such as, but not limited to the particular lookup value (e.g., a destination address of a packet).