Exact-Match Flow ID Generation via Serial CCT Circuits
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing packet switching technologies face inefficiencies in handling packets due to the lack of exact-match flow tables that can store wildcard indicators or mask values, leading to increased congestion and power consumption in crossbar switches, and require external processing for flow table updates.
Innovation Solution
An integrated circuit with an exact-match flow table structure that generates a unique Flow ID for packets, using SRAM to store flow entries with bit-by-bit exact-match capabilities, and employs a multiplexer circuit and programmable reduce table to determine actions, reducing the need for wildcard indicators and external processing.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If traditional packet switching technologies are used without exact-match flow tables, then the system can handle packets with wildcard indicators and mask values, but this leads to increased congestion and power consumption in crossbar switches
Solution Approach 1:
The flow table functionality is segmented from the crossbar switch into a separate exact-match flow table structure. This segmentation allows the crossbar switch to focus only on exact-match packet forwarding based on Flow IDs, eliminating the need for complex wildcard matching and mask value processing within the crossbar, thereby reducing congestion and power consumption.
Solution Approach 2:
An exact-match flow table structure acts as an intermediary between the packet input and the crossbar switch. This intermediary generates Flow IDs from incoming packets and performs exact-match lookups, converting complex packet matching requirements into simple Flow ID comparisons, which reduces the processing burden on the crossbar switch.
2Adaptability or versatility
If traditional flow tables with wildcard indicators are used, then the system can provide flexible packet matching, but this increases device complexity and requires external processing for flow table updates
Solution Approach 1:
The complexity of wildcard indicators and mask values is extracted from the flow table structure. The exact-match flow table stores only Flow IDs and associated actions without wildcard indicators or mask values. Complex matching logic is taken out and handled by the Flow ID generation process, which transforms packet data into Flow IDs that inherently encode the matching requirements.
Solution Approach 2:
The flow table matching parameter is changed from complex multi-field matching with wildcards to simple exact-match Flow ID comparison. This parameter change simplifies the flow table structure while maintaining matching flexibility through the design of the Flow ID generation process, which can incorporate various packet fields and transformation rules.
3Productivity
If exact-match flow tables are implemented without external processing, then the system reduces congestion and power consumption, but this requires eliminating wildcard indicators and mask values
Solution Approach 1:
Instead of having the flow table store complex matching patterns and perform wildcard matching, the system inverts the approach by having the Flow ID generation process perform the complex transformations and encoding, while the flow table performs only simple exact-match comparison. This inversion maintains matching versatility while enabling efficient exact-match processing.
Data Source
AI summary
An integrated circuit includes an input port, a first Characterize/Classify/Table Lookup and Multiplexer Circuit (CCTC), a second CCTC, and an exact-match flow table structure. The first and second CCTCs are structurally identical. The first and second CCTs are coupled together serially. In one example, an incoming packet is received onto the integrated circuit via the input port and packet information is supplied to a first characterizer of the first CCTC. Information flow passes through the classifier of the first CCT, through the Table Lookup and Multiplexer Circuit (TLMC) of the first CCT, through the characterizer of the second CCT, through the classifier of the second CCT, and out of the TLMC of the second CCT in the form of a Flow Id. The Flow Id is supplied to the exact-match flow table structure to determine whether an exact-match for the Flow Id is found in the flow table structure.