Non-Binary LDPC Decoding with Compressed Bit Reliability Values

Solution Overview

Problem

Non-binary low density parity check (LDPC) codes require complex computations and large storage spaces for reliability values, particularly in error correction operations, due to their definition in Galois fields, which can lead to increased power consumption and storage capacity needs.

Innovation Solution

An error correction device and method that determines bit reliability values based on soft decision bits and uses a decoder with variable nodes in a Galois field to restore reliability values, reducing the need for sign information and compressing reliability values, thereby reducing storage and power consumption.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If non-binary LDPC code is used for error correction, then error correction capability is improved, but storage space for reliability values and computation complexity increase

Engineering Contradiction:

Improveerror correction capabilityVSAvoidcomputation complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The reliability value is segmented into multiple bit reliability values, each corresponding to a specific bit position within the symbol. This segmentation allows the decoder to process and store reliability information in a more manageable form, reducing the overall storage requirement while maintaining error correction capability.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The invention extracts only the necessary bit reliability values from the full reliability value, discarding redundant information. By taking out only the essential components needed for decoding, the storage space and computation complexity are reduced while preserving the core error correction functionality.

Inventive Principle:

Principle #2Taking out (Extraction)

2Reliability

If non-binary LDPC code is used for error correction, then error correction capability is improved, but storage space for reliability values increases

Engineering Contradiction:

Improveerror correction capabilityVSAvoidstorage space for reliability values

Core Design Contradiction:

ReliabilityVSQuantity of substance

Solution Approach 1:

The reliability value is segmented into multiple bit reliability values, each corresponding to a specific bit position within the symbol. This segmentation allows the decoder to process and store reliability information in a more manageable form, reducing the overall storage requirement while maintaining error correction capability.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The invention extracts only the necessary bit reliability values from the full reliability value, discarding redundant information. By taking out only the essential components needed for decoding, the storage space and computation complexity are reduced while preserving the core error correction functionality.

Inventive Principle:

Principle #2Taking out (Extraction)

3Measurement precision

If full reliability values are stored in variable node, then decoding accuracy is improved, but storage capacity and power consumption increase

Engineering Contradiction:

Improvedecoding accuracyVSAvoidpower consumption

Core Design Contradiction:

Measurement precisionVSUse of energy by moving object

Solution Approach 1:

The invention extracts only the necessary bit reliability values from the full reliability value, discarding redundant information. By taking out only the essential components needed for decoding, the storage space and computation complexity are reduced while preserving the core error correction functionality.

Inventive Principle:

Principle #2Taking out (Extraction)

Solution Approach 2:

Instead of maintaining full precision reliability values throughout the decoding process, the invention uses compressed bit reliability values that are sufficient for each decoding iteration. This approach trades some precision for significant reductions in storage and energy requirements, similar to using disposable or temporary storage solutions.

Inventive Principle:

Principle #27Cheap short-living objects (Disposable)

Data Source

PatentUS10892779B2Error correction device, operating method thereof and electronic device including the same

Publication Date: 2021.01.12 SK HYNIX INC

AI summary

An error correction device includes a bit reliability value determination circuit configured to determine bit reliability values corresponding to hard decision bits, based on soft decision bit sets corresponding to the hard decision bits; and a decoder including a variable node configured to receive and store the hard decision bits and the bit reliability values, and perform a decoding operation for the hard decision bits by restoring reliability values from the bit reliability values. The reliability values correspond to elements except a decision symbol configured by the hard decision bits, in a Galois field (GF) defined in the variable node. All necessary reliability values are not transmitted to each variable node, instead, compressed reliability values are transmitted to the variable node. The variable node receives and retains the compressed reliability values, restores necessary reliability values, and uses them in a decoding operation.