Memory Controller L2P Mapping for O(1) SSD Data Search

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing data search algorithms in SSDs with volatile memory, such as DRAM, suffer from high time complexity, particularly for frequently accessed 'hot data, which can become a performance bottleneck when data quantity is large.

Innovation Solution

Implementing an expanded L2P mapping table that maps logical addresses to both volatile and non-volatile memory, reducing search complexity to O(1) by using dedicated circuits for parallel data search across both memory types.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Quantity of substance

If traditional data search algorithms are used in SSDs with volatile memory, then the system can handle large amounts of data, but the time complexity becomes high especially for frequently accessed hot data

Engineering Contradiction:
Improvedata quantityVSAvoidsearch time complexity
Core Design Contradiction:
Quantity of substanceVSLoss of time

Solution Approach 1:

The L2P mapping table is segmented into multiple segments, each stored in a separate volatile memory bank. This segmentation allows parallel search operations across multiple memory banks simultaneously, reducing the overall search time complexity from O(n) to O(1) for hot data while maintaining the ability to handle large data quantities.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent introduces a new dimension to the L2P mapping structure by organizing it as a multi-dimensional array with segment dimensions. This allows the search operation to access mapping information through multiple indexing dimensions (segment index, offset index), enabling constant-time access to mapping tables regardless of the total data quantity stored in the SSD.

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

2Loss of time

If an expanded L2P mapping table is implemented to map logical addresses to both volatile and non-volatile memory, then search complexity is reduced to O(1), but the device complexity increases

Engineering Contradiction:
Improvesearch time complexityVSAvoidmapping table structure
Core Design Contradiction:
Loss of timeVSDevice complexity

Solution Approach 1:

The L2P mapping table is divided into multiple segments stored in different volatile memory banks, with each segment containing a portion of the mapping information. This segmentation reduces the complexity of individual memory access operations while enabling parallel processing, achieving O(1) search complexity through structured division rather than monolithic table management.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent introduces segment index registers and offset index registers as intermediary structures between the logical address input and the volatile memory banks. These intermediaries simplify the complex mapping lookup process by breaking it into manageable steps: first determining the segment, then finding the specific entry within that segment, reducing the overall device complexity through structured intermediate processing.

Inventive Principle:
Principle #24Intermediary (Mediator)

Data Source

PatentEP4505268B1Memory controller and memory system performing data search
Publication Date: 2026.04.15 YANGTZE MEMORY TECH CO LTD
  • EP4505268B1 patent drawingFigure 1
  • EP4505268B1 patent drawingFigure 2A~2B
  • EP4505268B1 patent drawingFigure 3

AI summary

In certain aspects, a memory system includes a volatile memory device and a memory controller operatively coupled to the volatile memory device. The volatile memory device is configured to store a logical-to-physical (L2P) mapping table. The memory controller is configured to maintain the L2P mapping table stored in the volatile memory device, such that the L2P mapping table maps a first set of logical addresses to identifiers (IDs) of memory blocks of a cache, respectively.