Iterative Decoder Stall Detection With Adaptive Bit Flipping
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Bit Flipping (BF) decoders in memory subsystems can get stuck in stall conditions due to repeated parity violations, leading to increased latency and Quality of Service (QoS) issues, even at low raw bit error rates, as they fail to exit the stall condition effectively.
Innovation Solution
The implementation of an enhanced BF decoder that detects stall conditions by monitoring iteration counts and parity violation thresholds, modifying the bit flipping criterion to include reduced channel information impact or increased bit flipping thresholds, allowing the decoder to exit the stall condition and improve performance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a standard Bit Flipping decoder is used for error correction, then error correction capability is provided, but stall conditions occur leading to increased latency and QoS issues
Solution Approach 1:
The patent applies preliminary action by detecting stall conditions before they cause excessive latency. The decoder monitors parity violation counts during iterations and identifies when the decoder is entering a stall condition (when parity violations remain above a threshold after a certain number of iterations). By detecting this condition early, the system can intervene before the stall condition significantly increases latency, thus resolving the contradiction between maintaining error correction capability and avoiding time loss.
Solution Approach 2:
The patent applies parameter changes by dynamically adjusting the bit flipping criterion based on the detected stall condition. When a stall condition is detected, the system modifies the decoding parameters (such as changing the threshold for bit flipping or adjusting the number of iterations) to escape the stall condition. This allows the decoder to maintain reliability while reducing latency by adapting parameters in response to the detected condition.
2Measurement precision
If iterative decoding is performed to ensure error correction, then correction accuracy is improved, but stall conditions cause the decoder to fail to exit effectively
Solution Approach 1:
The patent applies feedback by continuously monitoring the parity violation count during the iterative decoding process and using this information to detect stall conditions. The system feeds back this detection information to control the decoding process, allowing it to identify when accuracy improvements are no longer being made (stall condition) and take corrective action to exit the stall condition, thus resolving the contradiction between maintaining correction accuracy and improving exit efficiency.
Solution Approach 2:
The patent applies dynamics by making the decoding process adaptive rather than static. The system dynamically adjusts its behavior based on the detected stall condition, changing the decoding strategy mid-process to escape from unproductive iteration patterns. This dynamic adaptation allows the decoder to maintain accuracy when needed while efficiently exiting stall conditions, resolving the contradiction between correction accuracy and exit efficiency.
Data Source
AI summary
Methods, systems, and apparatuses detect and mitigate a stall condition in an iterative decoder. A codeword is received from a memory device. One or more of the plurality of bits in the codeword are flipped in each of a plurality of error correction iterations. Each bit is flipped using a first bit flipping criterion that includes comparing a first bit flipping threshold and an energy function of each bit. Responsive to the determining an iteration count threshold is satisfied and a parity violation count threshold is satisfied, one or more of the plurality of bits in the codeword are flipped using a second bit flipping criterion for one or more error correction iterations. The second bit flipping criterion differs from the first bit flipping criterion.