Memory Controller Scrubbing Victim Pages to Prevent Heat Disturbance
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Nonvolatile memory devices, such as PCRAM, experience data disturbance due to heat generated during write operations, affecting adjacent memory cells and leading to program disturbance, read disturbance, and state drift, which degrades data reliability.
Innovation Solution
A memory system with a memory controller that counts write operations, identifies 'victim' pages exceeding a threshold, and performs a scrub operation by copying data from these pages to mitigate interference and maintain data integrity.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If write operations are performed frequently to improve data storage capability, then data storage reliability deteriorates due to heat-induced disturbance in adjacent memory cells
Solution Approach 1:
The patent applies preliminary action by performing scrub operations before disturbance occurs. The memory controller monitors write operation counts and proactively copies data from victim pages that are adjacent to frequently written pages, preventing heat-induced disturbance from corrupting the data before it happens.
Solution Approach 2:
The patent implements feedback by continuously monitoring write operation counts for each memory block and using this information to dynamically identify victim pages. The memory controller adjusts scrub operation targeting based on actual write patterns, focusing resources on pages most at risk from heat disturbance.
2Reliability
If scrub operations are performed on all pages to prevent disturbance, then data reliability improves, but system complexity and operation overhead increase
Solution Approach 1:
The patent applies local quality by differentiating treatment between different memory pages based on their proximity to frequently written pages. Only victim pages adjacent to high-write pages undergo scrub operations, while other pages maintain normal operation. This localized approach reduces overall operation overhead while protecting critical data.
Solution Approach 2:
The patent uses parameter changes by monitoring write operation counts as a threshold parameter to dynamically identify victim pages. When write counts exceed certain thresholds, adjacent pages are flagged for scrub operations. This parameter-based selection optimizes the balance between reliability and operation overhead.
3Productivity
If victim pages are identified and scrubbed selectively to reduce overhead, then operation efficiency improves, but disturbance protection may be insufficient
Solution Approach 1:
The patent implements feedback by continuously monitoring write operation counts and using this real-time information to accurately identify victim pages. The system adjusts scrub operation targeting based on actual write patterns, ensuring that pages most at risk from heat disturbance receive protection while minimizing unnecessary operations on safe pages.
Solution Approach 2:
The patent applies preliminary action by proactively identifying and protecting victim pages before disturbance occurs. By monitoring write counts and preemptively copying data from adjacent pages, the system ensures protection is in place before heat-induced disturbance can corrupt the data.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
The solution effectively reduces disturbance between adjacent memory cells, enhancing data reliability by refreshing or rewriting data in affected pages, thereby extending the lifespan of the memory device and preventing unnecessary scrub operations.
Implementation Method 1
the phase change material is changed to a crystal or amorphous phase by applying heat thereto
Implementation Method 2
When voltage and current are applied to the electrodes 1 and 3, high temperature is induced in the PCM layer 2
Data Source
AI summary
A memory system includes a memory device including one or more memory blocks, and configured to store data in a plurality of pages included in each memory block through a write operation, and a memory controller configured to count an operation number of write operations performed on the memory block, check whether the write operation is performed for each of the pages, select one or more victim pages among the pages, and copy data stored in the victim pages.