Soft-Information Bit Flipping Decoder for Low-Bandwidth ECC
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Bit flipping decoders, used for error correction in memory devices, face limitations in energy efficiency and error correction capability, particularly in mobile applications, as they rely on hard data and do not effectively utilize soft information, leading to increased energy consumption and reduced memory throughput.
Innovation Solution
The implementation of bit flipping decoders that utilize soft information to improve error correction capabilities, specifically by determining energy function values for codeword bits based on parity violations and channel information, allowing for reduced bandwidth consumption and enhanced error correction without significant impact on memory subsystem throughput.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If bit flipping decoders use hard data only for error correction, then device complexity is reduced, but error correction capability deteriorates
Solution Approach 1:
The patent segments the error correction process into two distinct phases: a first bit flipping decoder that processes hard data to correct dominant errors, and a second bit flipping decoder that processes soft information to correct residual errors. This segmentation allows the system to achieve high error correction capability while keeping each individual decoder relatively simple, as each decoder only needs to handle a specific portion of the error correction task rather than requiring a single complex decoder to handle all error types.
2Reliability
If bit flipping decoders process complete soft information for all codeword bits, then error correction capability is improved, but bandwidth consumption increases
Solution Approach 1:
The patent extracts and processes only the most critical soft information bits that correspond to positions where errors are most likely to occur, rather than processing soft information for all codeword bits. By identifying and extracting only the essential soft information needed for correcting residual errors after the first decoding phase, the system achieves improved error correction capability while minimizing bandwidth consumption associated with soft information transfer.
3Reliability
If bit flipping decoders use soft information, then error correction capability is improved, but energy consumption increases
Solution Approach 1:
The patent implements a periodic two-stage decoding process where the first bit flipping decoder processes hard data in an initial phase, and only if errors remain does the system proceed to the second phase where soft information is processed by a second bit flipping decoder. This periodic action allows the system to achieve improved error correction capability when needed while minimizing energy consumption by avoiding continuous soft information processing, making it suitable for mobile applications with energy constraints.
Data Source
AI summary
Methods, systems, and apparatuses include receiving a codeword stored in a memory device. Energy function values are determined for bits of the codeword based on soft information for the bits of the codeword. A bit of the codeword is flipped when the energy function values for a bit of the codeword satisfies a bit flipping criterion. A corrected codeword that results from the flipping of the bits is returned.