Flash Memory Mapping Table Search Optimization

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Traditional methods for updating logical address-physical address mapping tables in flash memory modules are inefficient, leading to increased search times for data reading due to the need to search both dynamic and static mapping tables, which affects the performance of memory management circuits.

Innovation Solution

A mapping table management method that uses a dynamic mapping table and relation management information in a buffer memory to quickly determine if the latest mapping information for a read operation is in the dynamic table, and if not, searches the static mapping table, improving the speed of finding physical addresses during data read operations.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If the traditional method of sequentially loading, updating, and storing the logical address-physical address mapping table is used, then the mapping information is kept updated, but the search time for data reading increases due to needing to search both dynamic and static mapping tables

Engineering Contradiction:
Improvemapping information accuracyVSAvoidsearch time
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The patent divides the mapping table into two separate segments: a dynamic mapping table stored in buffer memory for recently updated mappings, and a static mapping table stored in non-volatile memory for persistent mappings. This segmentation allows the system to search only the relevant table segment during read operations, reducing overall search time while maintaining accurate mapping information.

Inventive Principle:
Principle #1Segmentation

2Speed

If the dynamic mapping table is maintained separately in buffer memory, then the latest mapping information can be quickly accessed, but the device complexity increases due to managing multiple mapping tables

Engineering Contradiction:
Improvemapping search speedVSAvoidmapping table management complexity
Core Design Contradiction:
SpeedVSDevice complexity

Solution Approach 1:

The patent pre-loads frequently accessed mapping information into the dynamic mapping table in buffer memory before read operations occur. By preparing this quick-access table in advance and maintaining it alongside the static table, the system enables fast mapping lookups during read operations without requiring complex real-time management during actual data access.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentUS11573908B1Mapping table management method, memory control circuit unit and memory storage device
Publication Date: 2023.02.07 HEFEI CORE STORAGE ELECTRONICS LTD
  • US11573908B1 patent drawing
  • US11573908B1 patent drawing
  • US11573908B1 patent drawing

AI summary

A mapping table management method, a memory control circuit unit, and a memory storage device are provided. The method includes: receiving a read command from a host system, wherein the read command indicates reading a first data stored in at least one first logical address; and searching whether a relation management information reflects that a first group static mapping table recording the first logical address is related to a dynamic mapping table. In response to a search result reflecting that the first group static mapping table is related to the dynamic mapping table, the dynamic mapping table is searched to obtain a first physical address mapped by the first logical address. And if not related, the first group static mapping table among group static mapping tables is searched to obtain a second physical address mapped by the first logical address.