DRAM-Based TCAM Cell Reduces Chip Area and Search Latency
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional TCAMs based on static random-access memories (SRAMs) face challenges with high power consumption and area density, limiting their suitability for energy-constrained applications, and emerging memory-based TCAMs struggle with limited endurance and on/off ratio, making it difficult to distinguish between match and mismatch states in large datasets.
Innovation Solution
A DRAM-like memory-based TCAM structure with a 6TOC unit cell, featuring two storage elements and two search transistors, provides un-limited data update frequency, fast search latency, and a large on/off ratio, enabling efficient in-memory search functions for applications like routers, database searches, and neuromorphic computing.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If SRAM-based TCAM is used, then search functionality is provided, but area consumption and power consumption are large
Solution Approach 1:
The patent changes the memory type parameter from static (SRAM) to dynamic (DRAM), fundamentally altering the storage mechanism. This allows using fewer transistors per cell (6T vs 16T) while maintaining search functionality through periodic refresh operations, directly resolving the area consumption contradiction
Solution Approach 2:
The patent introduces dynamic refresh operations to the TCAM structure. The DRAM-based cells require periodic refreshing to maintain stored data, transforming the static search structure into a dynamic one. This enables reduced area while preserving search capability through time-based maintenance operations
2Area of stationary object
If emerging memory-based TCAM is used, then area density is improved, but on/off ratio is insufficient for large array searches
Solution Approach 1:
The patent changes the memory material parameter from emerging memories (RRAM, PCM, FeFET) to conventional DRAM technology. This provides a well-established high on/off ratio in the dynamic transistor, ensuring clear distinction between match and mismatch states even in large arrays, while maintaining improved area density
3Area of stationary object
If emerging memory-based TCAM is used, then area density is improved, but endurance is limited constraining data update frequency
Solution Approach 1:
The patent changes the memory technology parameter from emerging memories with limited write endurance to conventional DRAM with superior write durability. DRAM cells can be refreshed and rewritten continuously without degradation, enabling high-frequency data updates while maintaining the area density benefits of dynamic memory architecture
Data Source
AI summary
An in-dynamic memory search device and an operation method thereof are provided. The in-dynamic memory search device includes at least one word line, at least two bit lines, at least one match line, at least one unit cell, at least two search lines, at least one pre-charge unit and at least one sense unit. The unit cell includes two storage elements and two search transistors. Each of the storage elements includes a write transistor and a read transistor. The write transistor is connected to the word line and one of the bit lines. The read transistor is connected to the write transistor and the match line. The search transistors are respectively connected to the read transistors. The search lines are respectively connected to the search transistors. The pre-charge unit is connected to the match line. The sense unit is connected to the match line.