Memory Data Path Selection with PEC-Adaptive RBER Thresholds
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional memory sub-systems face challenges in balancing latency and reliability during data path selection due to varying raw bit error rates (RBER) across the drive life of a memory device, particularly influenced by program-erase cycles (PEC).
Innovation Solution
Implementing an adaptive data path selection threshold in memory sub-systems that adjusts RBER thresholds based on different PEC ranges, using a look-up table to determine the appropriate threshold for each PEC stage, thereby optimizing latency and reliability through dynamic ECC decoding operations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If a fixed RBER threshold is used for data path selection, then the system is simple to operate, but it cannot adapt to varying error rates across the drive life, resulting in suboptimal performance
Solution Approach 1:
The patent implements dynamic RBER thresholds that automatically adjust based on program-erase cycle counts. The system transitions from static to dynamic threshold selection, allowing the data path selection criteria to adapt to the memory device's aging and wear state without requiring manual intervention or complex external control systems.
Solution Approach 2:
The system changes the RBER threshold parameter based on PEC ranges. Different threshold values are applied at different stages of the memory device's life, with higher thresholds for younger devices and lower thresholds for older devices. This parameter adaptation resolves the contradiction by making the system both adaptive and manageable through predefined parameter sets.
2Reliability
If ECC decoding is always performed, then data reliability is improved, but latency increases
Solution Approach 1:
The patent applies partial ECC decoding only when necessary, rather than always performing full ECC decoding. By using RBER threshold comparisons to determine when ECC is needed, the system performs the minimum necessary error correction actions, reducing unnecessary latency while maintaining reliability when errors are present.
Solution Approach 2:
The system dynamically adjusts the decision parameter (RBER threshold) based on PEC ranges. For younger memory devices with lower error rates, higher thresholds allow skipping ECC decoding to reduce latency. For older devices with higher error rates, lower thresholds trigger ECC decoding to ensure reliability. This parameter adaptation optimizes the trade-off between reliability and latency across the device lifecycle.
3Speed
If ECC decoding is skipped to reduce latency, then speed is improved, but data reliability deteriorates
Solution Approach 1:
The patent changes the RBER threshold parameter based on PEC ranges to dynamically control when ECC decoding occurs. For younger memory devices, higher thresholds enable skipping ECC decoding to maximize speed. For older devices, lower thresholds ensure ECC decoding occurs to maintain reliability. This resolves the contradiction by making speed optimization conditional on the device's age and error characteristics.
Solution Approach 2:
The system performs partial error correction only when RBER exceeds the adaptive threshold, rather than always performing full ECC decoding or never performing it. This selective approach achieves the minimum necessary error correction to maintain reliability while minimizing latency, resolving the speed-reliability trade-off.
4Productivity
If adaptive RBER thresholds based on PEC ranges are implemented, then performance is optimized across drive life, but the system complexity increases
Solution Approach 1:
The patent segments the memory device's operational life into discrete PEC ranges, each with its own optimized RBER threshold. This segmentation allows performance optimization for different aging stages while keeping each segment's management simple through predefined threshold values, rather than requiring continuous complex adjustments.
Solution Approach 2:
The system uses predefined RBER threshold parameters for different PEC ranges to achieve adaptive performance optimization. By establishing fixed parameter sets for different operational stages, the system gains the benefits of adaptation without the complexity of real-time dynamic calculation, resolving the contradiction between performance optimization and system complexity.
Data Source
AI summary
A threshold criterion of a plurality of threshold criteria is identified based on a current program-erase cycle (PEC) count of a first block of a memory device, wherein the first block is configured as quad-level cell (QLC) memory. A raw bit error rate (RBER) associated with data of a second block of the memory device is determined, wherein the second block is configured as single-level cell (SLC) memory. It is determined that the RBER associated with the data of the second block satisfies the threshold criterion. In response to determining that the RBER satisfies the threshold criterion, the data of the second block is written to the first block.