SED Parity Erasure Correction for MLC Flash ECC Codewords

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Multi-Level Cell (MLC) flash memory devices experience increased bit error rates due to merging of threshold voltage distribution profiles, leading to unreliable data storage and erasures, which existing error correction methods struggle to effectively address.

Innovation Solution

Implementing single error detection (SED) parity bits and soft read information to correct erasures prior to ECC decoding, allowing for a reduced number of bit errors in the ECC codeword, thereby enhancing error correction capability and extending the useful life of data storage devices.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Quantity of substance

If MLC flash memory devices store multiple bits per cell to increase storage density, then storage density is improved, but bit error rate increases due to merging of threshold voltage distribution profiles

Engineering Contradiction:
Improvestorage densityVSAvoidbit error rate
Core Design Contradiction:
Quantity of substanceVSReliability

Solution Approach 1:

The patent segments the error correction process into two distinct stages: first using SED parity bits to detect and correct single bit errors, then using ECC parity bits to correct remaining errors. This segmentation allows each correction mechanism to be optimized for its specific function, improving overall reliability while maintaining storage density.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent performs preliminary error correction using SED parity bits before applying ECC decoding. By detecting and correcting single bit errors in advance, the system reduces the burden on the ECC decoder and improves the overall error correction capability, thereby enhancing reliability without sacrificing storage density.

Inventive Principle:
Principle #10Preliminary action

2Reliability

If traditional ECC parity bits are used for error correction, then error correction capability is provided, but the capability is limited compared to the proposed SED parity bit approach

Engineering Contradiction:
Improveerror correction capabilityVSAvoidparity bit structure
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent divides the parity bit structure into two segments: SED parity bits for single error detection and correction, and ECC parity bits for broader error correction. This segmentation enables the system to achieve superior error correction capability by combining the strengths of both approaches, while the modular structure manages complexity effectively.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The SED parity bits act as an intermediary layer between the stored data and the ECC decoding process. They provide preliminary error detection and correction, serving as a mediator that prepares the data for more comprehensive ECC processing, thereby enhancing overall error correction capability.

Inventive Principle:
Principle #24Intermediary (Mediator)

3Measurement precision

If soft read operations are performed at offset voltages to detect erasures, then erasure detection is improved, but additional read operations increase time consumption

Engineering Contradiction:
Improveerasure detection accuracyVSAvoidread operation time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent performs soft read operations at offset voltages as a preliminary step to identify potential erasures before committing to full error correction procedures. This preliminary detection mechanism improves measurement precision by accurately identifying erasures, while the early detection allows for more efficient subsequent processing that minimizes time loss.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentUS8996950B2Erasure correction using single error detection parity
Publication Date: 2015.03.31 SANDISK TECHNOLOGIES LLC
  • US8996950B2 patent drawing
  • US8996950B2 patent drawing
  • US8996950B2 patent drawing

AI summary

A method includes receiving a representation of a set of single error detection (SED) parity bits and a representation of data. The data includes an error correction coding (ECC) codeword including information bits and ECC parity bits. Each SED parity bit of the set of SED parity bits indicates a parity value for a corresponding portion of the data. The method includes, in response to determining that a particular portion of the representation of the data includes a single erasure bit, selectively modifying a bit value of the single erasure bit based on the representation of the SED parity bit that corresponds to the particular portion and generating an updated representation of the ECC codeword when the bit value of the single erasure bit corresponds to the ECC codeword and has been modified. The method may include initiating an ECC decode operation of the updated representation of the ECC codeword.