Dynamic Threshold Data Copying in Memory Dies

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Non-volatile memory devices face challenges in balancing data copying speed with error correction, as copying data without error detection and correction increases the risk of data becoming unrecoverable due to accumulated errors, while full error correction procedures introduce latency.

Innovation Solution

A system determines whether to perform a full copy with error correction or a 'copy-back' operation based on predefined parameters and dynamically computed thresholds, considering factors like error counts, write/erase cycles, and metadata importance to optimize between speed and data integrity.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If full error detection and correction procedures are used during data copying, then data integrity is improved, but copying speed deteriorates due to increased latency

Engineering Contradiction:
Improvedata integrityVSAvoidcopying speed
Core Design Contradiction:
ReliabilityVSSpeed

Solution Approach 1:

The system dynamically adjusts the copying procedure by computing thresholds based on memory device age and write/erase cycles. When error risk exceeds the dynamic threshold, full error correction is applied; otherwise, faster copy-back procedure is used. This dynamic adaptation resolves the contradiction by optimizing the balance between reliability and speed based on actual memory conditions.

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The invention changes the parameter of error correction application from a static always-on approach to a conditional approach based on computed thresholds. By monitoring parameters like memory age and cycle count, the system adjusts whether to apply full error correction or use faster copying, thereby resolving the speed-integrity tradeoff.

Inventive Principle:
Principle #35Parameter changes

2Speed

If copy-back procedure without error correction is used, then copying speed is improved, but data reliability deteriorates due to accumulated errors

Engineering Contradiction:
Improvecopying speedVSAvoiddata integrity
Core Design Contradiction:
SpeedVSReliability

Solution Approach 1:

The system implements feedback by continuously monitoring memory device age and write/erase cycle counts, comparing these against dynamic thresholds. This feedback mechanism determines whether to apply error correction or use copy-back procedure, ensuring that speed optimizations do not compromise data integrity when error risk becomes too high.

Inventive Principle:
Principle #23Feedback

Solution Approach 2:

The system performs preliminary assessment by computing thresholds based on memory age and cycle count before executing the copy operation. This preliminary action determines the appropriate copying method in advance, preventing error accumulation while maintaining optimal speed by selecting the right procedure before data copying begins.

Inventive Principle:
Principle #10Preliminary action

3Adaptability or versatility

If dynamic thresholds based on memory age and cycle count are computed, then adaptability is improved, but device complexity increases

Engineering Contradiction:
Improvecopy strategy adaptabilityVSAvoidthreshold computation complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The system segments the copying process into distinct procedures (full error correction vs. copy-back) selected based on dynamic thresholds. This segmentation allows the complex adaptability of threshold-based decision-making to be applied only where needed, while simpler procedures can be used otherwise, managing device complexity through structured division of operations.

Inventive Principle:
Principle #1Segmentation

Data Source

PatentUS9158621B2System and method of copying data
Publication Date: 2015.10.13 SANDISK TECHNOLOGIES LLC
  • US9158621B2 patent drawing
  • US9158621B2 patent drawing
  • US9158621B2 patent drawing

AI summary

A method of copying data includes receiving a command instructing copying of data from a source location in the memory die to a destination location in the memory die. The method includes determining if a criterion is met, including comparing a predefined parameter to a dynamic threshold. In response to determining that the criterion is met, the method includes executing the copying by moving the data from the source location in the memory die to the controller die and, after moving the data to the controller die, moving an error-corrected version of the data from the controller die to the destination location in the memory die. In response to determining that the criterion is not met, the method includes executing the copying by moving the data inside the memory die source location to the destination location without moving the data to the controller die.