Irregular LDPC Encoder Architecture With Reduced Matrix Computation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional LDPC encoders are inefficient in terms of area and power consumption when handling irregular LDPC codes, which are necessary for improving the reliability of NAND flash memory systems, particularly in triple level cell programming.
Innovation Solution
The development of an irregular LDPC encoder architecture that utilizes a parity check matrix format with a Richardson-Urbanke algorithm, where portion T is an identity matrix, reducing dense matrix calculations and allowing for efficient storage and processing of parity information, thereby minimizing power consumption and area requirements.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If conventional LDPC encoders are used for irregular LDPC codes, then encoding capability is provided, but area and power consumption are excessive
Solution Approach 1:
The parity check matrix is segmented into six distinct portions (A, B, C, D, E, and T), where each portion is processed separately through dedicated calculation blocks. This segmentation allows the encoder to handle irregular LDPC codes by breaking down the complex matrix operations into manageable segments, reducing the overall area requirement compared to processing the entire matrix as a single unit.
Solution Approach 2:
The invention changes the parameter structure of the parity check matrix by setting portion T as an identity matrix and defining specific relationships between the six portions. This parameter transformation enables the use of the Richardson-Urbanke algorithm, which optimizes the encoding process for irregular LDPC codes while reducing computational complexity and encoder area.
2Reliability
If conventional LDPC encoders are used for irregular LDPC codes, then encoding capability is provided, but power consumption is excessive
Solution Approach 1:
The invention extracts and eliminates redundant dense matrix calculations by identifying that portion T is an identity matrix and utilizing the specific structural relationships between the six portions. This extraction of unnecessary computations directly reduces power consumption while maintaining the encoding capability for irregular LDPC codes.
Solution Approach 2:
By transforming the parity check matrix parameters to include an identity matrix portion and establishing specific relationships between portions, the invention reduces the computational burden and associated power consumption. The Richardson-Urbanke algorithm leverages these parameter changes to minimize energy-intensive operations.
3Measurement precision
If dense matrix calculations are performed for irregular LDPC codes, then encoding accuracy is maintained, but processing burden and memory logic requirements increase
Solution Approach 1:
The segmentation of the parity check matrix into six portions allows the encoder to process only the necessary segments with appropriate calculation methods. Sparse matrix operations are applied where applicable, and dense calculations are minimized to only where required, thereby maintaining encoding accuracy while reducing processing burden and memory logic requirements.
Solution Approach 2:
The parameter transformation that sets portion T as an identity matrix and defines specific relationships between portions enables the use of optimized algorithms that reduce computational complexity. This maintains encoding accuracy by preserving the essential mathematical relationships while eliminating redundant calculations.
Data Source
AI summary
A first memory location stores circulant contents of portions A, C, E, and B of a parity check matrix H. A second memory location stores circulant column counts of the portions A, C, E, and B. A third memory location stores a dense matrix equal to (ET−1B+D)−1, where T is an identity matrix and D and T are also portions of the parity check matrix H. First and second parity information is generated in response to receiving information data. Generating the first and second parity information includes accessing the circular content of the portions A, C, E, and B of a parity check matrix H and accessing the circulant column counts of the portions A, C, E, and B.