NAND Read Retry Table Indexing for Retention-Degraded SSD Data

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Flash memory in SSDs experiences charge loss leading to bit read errors due to degradation, necessitating inefficient and time-consuming read retry processes to maintain accurate memory readout.

Innovation Solution

Implement an adaptive read retry process using a pattern of retry voltage index sets determined by an aging parameter of the SSD, such as P/E cycles, temperature, or elapsed time, to quickly and efficiently compensate for charge loss.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If a sequential read retry process using a read retry table is implemented, then bit read errors caused by charge loss can be compensated, but the readout process becomes time-consuming and inefficient

Engineering Contradiction:
Improvebit read error compensationVSAvoidread retry time
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The system performs preliminary determination of the aging parameter (such as number of P/E cycles, temperature, or elapsed time) before initiating the read retry process. This preliminary action allows the system to pre-identify the appropriate voltage index set from the read retry table, avoiding the need to sequentially try multiple voltage sets and significantly reducing read retry time while maintaining reliable error compensation

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system changes the parameter selection approach by using the determined aging parameter to directly index into the read retry table and select the appropriate voltage index set. This parameter-based selection mechanism replaces the sequential trial approach, enabling efficient direct access to the correct read parameters without time-consuming iteration

Inventive Principle:
Principle #35Parameter changes

2Reliability

If multiple voltage index sets are sequentially tested, then charge loss degradation can be addressed, but computational resources are consumed and system efficiency decreases

Engineering Contradiction:
Improvecharge loss compensationVSAvoiddata retrieval efficiency
Core Design Contradiction:
ReliabilityVSProductivity

Solution Approach 1:

The system performs preliminary determination of the aging parameter before the read retry process, which enables direct selection of the appropriate voltage index set. This preliminary action eliminates the need for sequential testing of multiple voltage sets, significantly reducing computational resource consumption and improving data retrieval efficiency while maintaining reliable charge loss compensation

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system uses a pre-existing read retry table that contains copy备ed voltage index sets corresponding to different aging conditions. By determining the current aging parameter and indexing into this pre-prepared table, the system retrieves the appropriate voltage settings without needing to perform complex computational searches or sequential tests, thereby improving productivity

Inventive Principle:
Principle #26Copying

Data Source

PatentEP4679430A1An adaptive method to efficiently read out retention degraded NAND data
Publication Date: 2026.01.14 LENOVO (SINGAPORE) PTE LTD
  • EP4679430A1 patent drawingFigure 1A~1B
  • EP4679430A1 patent drawingFigure 1C
  • EP4679430A1 patent drawingFigure 2A~2B

AI summary

A method of operating a computing device with a solid state drive (SSD) includes: obtaining a preexisting read retry table that includes a sequential list of voltage index sets for reading a flash memory of the SSD; determining an aging parameter of the SSD; identifying a retry voltage index set from the sequential list based on the aging parameter; and reading the flash memory using the retry voltage index set.