Pre-computation TCAM Reduces Match Line Pre-charge Power
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current TCAM devices consume significant power due to the extensive pre-charging and discharging of match lines during search operations, as most match lines are discharged even though only a fraction may actually match the search word.
Innovation Solution
A pre-computation based TCAM architecture that utilizes a secondary TCAM to determine which match lines in the primary TCAM need to be pre-charged by storing pre-computation words representing the range of logic ones in data words, thereby disabling unnecessary pre-charging based on the count of logic ones in the search word.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If all match lines are pre-charged during search operations, then complete search coverage is ensured, but power consumption increases significantly
Solution Approach 1:
The patent applies preliminary action by pre-computing and storing the number of logic ones for each data word in a secondary TCAM before the actual search operation. This preliminary information is used to determine which match lines need to be pre-charged, avoiding unnecessary pre-charging and reducing power consumption while maintaining complete search coverage.
Solution Approach 2:
The patent introduces an intermediary mechanism - a secondary TCAM that stores pre-computed information about the number of logic ones in each data word. This intermediary structure mediates between the search input and the primary TCAM, enabling intelligent selection of match lines to pre-charge based on the search word's logic one count, thus resolving the contradiction between complete search coverage and power consumption.
2Use of energy by moving object
If a secondary TCAM is added for pre-computation, then power consumption is reduced, but device complexity increases
Solution Approach 1:
The patent applies universality by designing the secondary TCAM to serve multiple functions: it stores pre-computed logic one counts, acts as a filter for determining which match lines to pre-charge, and enables power reduction without requiring separate complex control logic. This multi-functionality justifies the added structure by consolidating multiple roles into a single component.
3Loss of energy
If pre-computation is performed using a secondary TCAM, then unnecessary pre-charging is avoided, but additional memory resources are required
Solution Approach 1:
The patent applies parameter changes by transforming the search problem from comparing entire data words to comparing the count of logic ones. Instead of storing and comparing full data words in the secondary TCAM, only the condensed parameter (number of logic ones) is stored, significantly reducing the memory resources required while still enabling effective filtering of non-matching entries.
Data Source
AI summary
A pre-computation based TCAM configured to reduce the number of match lines being pre-charged during a search operation to save power is disclosed. The pre-computation based TCAM stores additional information in a secondary TCAM that can be used to determine which match lines in a primary TCAM storing data words to be searched need not be pre-charged because they are associated with data words guaranteed to not match. The additional information stored in secondary TCAM can include a pre-computation word that represents a range inclusive of a lower and upper bound of a number of ones or zeroes possible in a corresponding data word stored in the primary TCAM.