Optical TCAM Search Using Digital Light Processing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Ternary Content Addressable Memory (TCAM) in network routers faces challenges with high power consumption, and existing solutions such as magnetism and optical Random-Access Memory (RAM) have limitations in addressing this issue effectively.
Innovation Solution
The use of a Digital Light Processing System (DLP) with a 2-Dimensional array of digital micro mirrors to direct and reflect light from input sources onto a detection screen, generating a resultant pixel that corresponds to the search result for input queries in the TCAM, enabling efficient search operations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If traditional TCAM is used for route lookup, then search speed is fast (parallel search in single cycle), but power consumption is high
Solution Approach 1:
The patent replaces the traditional electrical/magnetic TCAM system with an optical system using DLP technology. Light from input sources is reflected by micro-mirrors arranged according to TCAM content, and the reflected light patterns are detected to perform searches. This optical substitution eliminates the high power consumption of electrical TCAM while maintaining fast search capability through the inherent parallelism of light reflection.
Solution Approach 2:
The patent creates optical copies of TCAM data by arranging micro-mirrors to reflect light patterns that represent stored data. Each mirror's position and reflection state encodes data bits, allowing multiple data copies to be simultaneously represented in the optical field. This enables parallel search operations without requiring high-power electrical switching of individual memory cells.
2Use of energy by moving object
If optical RAM is used to address power consumption, then power consumption is reduced, but search capability and speed are limited
Solution Approach 1:
The patent segments the optical system into distinct functional components: light sources corresponding to input bits, micro-mirrors arranged in arrays representing TCAM data rows and columns, and detection screens for reading results. This segmentation allows each component to operate independently and efficiently, with light sources providing low-power illumination and micro-mirrors performing passive optical routing based on their physical arrangement.
Solution Approach 2:
The patent transitions from electrical domain operations to optical domain operations, adding the dimension of spatial arrangement through 2D micro-mirror arrays. Data is encoded not just in binary states but in the spatial positions and reflection angles of mirrors, enabling parallel search across multiple data dimensions simultaneously without increasing power consumption.
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 approach allows for high-speed searches, supporting over 100 billion searches per second and reduces power consumption by leveraging the switching speeds of micro-mirrors, while also enabling multiple color searches on the same TCAM.
Implementation Method 1
arranging, in a Digital Light Processing System (DLP), plurality of mirrors for directing the light from one or more input sources, over a detection screen
Data Source
AI summary
Present disclosure relates to a method and a system for searching through a Ternary Content Addressable Memory (TCAM). The system comprises a Digital Light Processing System (DLP) receiving an input query. The DLP comprises a 2-Dimensional array of digital micro mirrors configured for reflecting light from one or more input sources in the TCAM to a predefined position. The system further comprises a detection screen having a detection area. The detection area is configured for generating an image of a resultant pixel according to the reflection of the light, wherein the resultant pixel corresponds to a search result for an input query.