Ternary Content Addressable Memory for SDN Power Reduction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional ternary content addressable memory devices face challenges with high power consumption and limited flexibility in word length due to their inability to adapt to variable word lengths and the OpenFlow protocol's characteristics, which leads to inefficient packet forwarding in software defined networking.
Innovation Solution
A ternary content addressable memory device is designed with a pre-filter module using NAND-type memory for the first part of the forwarding rule and a searching module using NOR-type memory for the second part, allowing for flexible word length adjustment and power reduction through a pipeline register module with a field-effect transistor for energy-saving discharge.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If conventional ternary content addressable memory is used with fixed words length, then the device structure is simple, but the flexibility in words length is poor and cannot adapt to OpenFlow protocol characteristics
Solution Approach 1:
The patent divides the forwarding rule into two parts: a first part stored in NAND-type TCAM and a second part stored in NOR-type TCAM. This segmentation allows the system to handle variable word lengths by selectively using different memory types for different portions of the rule, thereby improving flexibility without requiring complete redesign of the memory structure.
Solution Approach 2:
The patent introduces a dynamic configuration mechanism where the word length can be adjusted based on the specific networking requirements and OpenFlow protocol characteristics. The system can dynamically select which part of the forwarding rule to match in which memory type, enabling adaptive word length configuration rather than being fixed.
2Reliability
If conventional ternary content addressable memory charges all match lines for each search, then the search operation is complete, but the power consumption is high due to discharge of mismatched match lines
Solution Approach 1:
The patent segments the matching process into two stages: first matching the first part of the forwarding rule in NAND-type TCAM, then matching the second part in NOR-type TCAM only if the first match succeeds. This segmentation ensures search completeness while reducing power consumption by avoiding unnecessary charging and discharging of match lines for the second part when the first part already mismatches.
Solution Approach 2:
The patent performs a preliminary match in the NAND-type TCAM before proceeding to the NOR-type TCAM match. This preliminary action filters out non-matching entries early, preventing the need to charge and subsequently discharge match lines in the second memory type, thereby reducing overall power consumption while maintaining complete search coverage.
3Use of energy by moving object
If technical means to reduce power consumption are applied, then the power consumption of match line is reduced, but the words length remains short and invariable
Solution Approach 1:
The patent merges two different TCAM types (NAND-type and NOR-type) with complementary characteristics into a unified system. The NAND-type TCAM provides power-efficient preliminary matching, while the NOR-type TCAM enables flexible word length configuration. This combination allows the system to achieve both reduced power consumption and variable word length capability simultaneously.
Solution Approach 2:
The patent creates a universal TCAM architecture that can handle multiple functions: power-efficient matching for fixed patterns and flexible variable-length pattern matching. The system can adaptively use different memory types for different matching requirements, making it universally applicable to various OpenFlow protocol scenarios with different word length requirements.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
This solution enhances the flexibility of word length and reduces power consumption by enabling efficient packet forwarding in software defined networking, improving the performance of ternary content addressable memory devices.
Implementation Method 1
When the first matching result indicates mismatch, the field-effect transistor is turned on to discharge to ground, thereby disabling the searching module
Data Source
AI summary
The present disclosure illustrates a ternary content addressable memory (TCAM) device for software defined networking and method thereof. In the TCAM device, M bits of each forwarding rule is stored as a first part into a NAND-Type TCAM, and N bits of the same forwarding rule is stored as a second part into a NOR-Type TCAM. M bits of searching data is compared with the first part to generate a first matching result, N bits of the searching data is compared with the second part to generate a second matching result when the first matching result indicates match, and comparing process for the second part is disabled when the first matching result indicates mismatch. The mechanism is help to improve flexibility of the TCAM in words length and to reduce power consumption.