Concatenated Error Correction Coding With Local Decoding for Low Latency
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Error correction coding schemes face a tradeoff between latency and data accuracy in memory devices, where longer codewords improve accuracy but increase latency, and shorter codewords reduce latency but decrease data storage capacity and require more computational resources.
Innovation Solution
A generalized concatenated error correction coding scheme that encodes data into sub-codewords with fewer check symbols, allowing for local decoding, and combines these into larger codewords with additional check symbols for enhanced error correction, enabling partial decoding and reducing latency while maintaining high data accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If longer codewords are used, then data accuracy is improved, but latency increases
Solution Approach 1:
The patent divides a long codeword into multiple shorter sub-codewords that can be decoded independently and in parallel. This segmentation allows partial decoding to occur before the entire codeword is received, reducing latency while maintaining the error correction capability of the original long codeword structure through a hierarchical decoding approach.
2Loss of time
If shorter codewords are used, then latency is reduced, but data storage capacity decreases
Solution Approach 1:
The patent combines multiple shorter sub-codewords into a larger codeword structure where sub-codewords are grouped and additional check symbols are added at the group level. This merging allows the system to achieve the low latency benefits of short codewords while recovering storage capacity through efficient grouping and shared redundancy mechanisms.
3Reliability
If more check symbols are used, then error correction capability is improved, but overhead increases
Solution Approach 1:
The patent implements local quality by adding check symbols at two different levels: within each sub-codeword for local error correction, and across groups of sub-codewords for enhanced error correction. This localized approach allows the system to provide strong error correction capability where needed while minimizing overall overhead through efficient distribution of check symbols.
Data Source
AI summary
A method for storing data within a memory device includes receiving data to be stored. The received data is encoded. The encoded data is stored within the memory device. Encoding the received data includes encoding the data into two or more sub-codewords. Each of the two or more sub-codewords includes a plurality of outer codewords. Two or more of the plurality of outer codewords are grouped to form a larger codeword that is larger than each of the plurality of outer codewords and the larger codeword is constructed to correct errors and/or erasures that are not correctable by the plurality of outer codewords, individually.