Syndrome Weight Memory Cell Performance Evaluation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The performance of non-volatile memory cells degrades over time, leading to reduced storage reliability, and existing methods for estimating their performance are inadequate in accurately assessing readout performance and selecting optimal read thresholds.
Innovation Solution
A memory system that calculates a syndrome weight based on readouts from multiple thresholds to estimate the number of errors in a code word and evaluates performance measures, allowing for the selection of appropriate read thresholds and ECC decoding configurations to improve readout performance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If multiple read thresholds are used to improve readout accuracy, then measurement precision is improved, but device complexity increases
Solution Approach 1:
The patent segments the readout process by dividing it into multiple read operations, each using a different read threshold. This allows the system to sample memory cells at multiple voltage levels to improve accuracy while managing complexity through structured segmentation of the sensing operation.
Solution Approach 2:
The patent performs multiple read operations with different thresholds, using more sampling actions than a single read would provide. This excessive sampling approach improves measurement precision by gathering more data points, with the syndrome weight calculation efficiently processing the additional information.
2Reliability
If syndrome weight calculation is performed based on multiple readouts, then reliability is improved, but use of energy increases
Solution Approach 1:
The patent replaces complex physical sensing operations with a computational approach using syndrome weight calculation from LDPC codes. Instead of performing multiple full read operations, the system uses the syndrome weight as a computational metric to evaluate readout quality, reducing the need for repeated physical sensing and thereby lowering power consumption while maintaining reliability assessment accuracy.
3Measurement precision
If multiple read operations are performed to evaluate performance, then measurement precision is improved, but loss of time increases
Solution Approach 1:
The patent extracts the essential performance information by calculating the syndrome weight from the readout data, rather than performing complete performance evaluations through multiple full read operations. This extraction approach captures the critical error information needed for reliability assessment while significantly reducing the time required for performance evaluation.
Solution Approach 2:
The patent uses the syndrome weight as a computational copy or representation of the actual error conditions in the memory cells. This syndrome copy provides sufficient information for performance evaluation without requiring direct observation of all possible error states, thereby reducing evaluation time while maintaining measurement precision.
Data Source
AI summary
A memory system includes an interface and storage circuitry. The interface is configured to communicate with a plurality of memory cells that store data by setting the memory cells to analog voltages representative of respective storage values. The storage circuitry is configured to read from a group of the memory cells a code word encoded using an Error Correction Code (ECC), by sensing the memory cells using at least first and second read thresholds for producing respective first and second readouts, to calculate, based on at least one of the first and second readouts, (i) a syndrome weight that is indicative of an actual number of errors contained in the code word, and (ii) a mid-zone count of the memory cells for which the first readout differs from the second readout, and, to evaluate a performance measure for the memory cells, based on the calculated syndrome weight and mid-zone count.