Memory Refresh Scheduling for Weak Retention Cells
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing memory systems face challenges in accommodating weaker retention memory cells while adhering to refresh parameters, leading to increased power consumption, die size, and refresh overhead, and failing to meet defined refresh thresholds.
Innovation Solution
Implementing a Low Overhead Retention Aware Refresh (LORAR) scheme that identifies and programs additional fuses for weaker retention cells, allowing for separate refresh operations with longer and shorter intervals, reducing refresh power and die size impact.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional refresh operations are used for all memory cells, then refresh parameters are met, but power consumption and die size increase
Solution Approach 1:
The patent segments memory cells into two categories: first memory cells with weaker retention characteristics and second memory cells with stronger retention characteristics. This segmentation allows different refresh strategies to be applied to each group, reducing overall power consumption while maintaining reliability for the weaker cells that require more frequent refreshes.
Solution Approach 2:
The patent applies local quality by providing enhanced refresh operations specifically to first memory cells with weaker retention characteristics, while using standard refresh operations for second memory cells with stronger retention. This localized approach ensures that only the cells needing additional attention receive extra refresh resources, optimizing power consumption and die size.
2Reliability
If traditional refresh operations are used for all memory cells, then refresh parameters are met, but die size increases
Solution Approach 1:
The patent segments memory cells into two categories: first memory cells with weaker retention characteristics and second memory cells with stronger retention characteristics. This segmentation allows different refresh strategies to be applied to each group, reducing overall die size while maintaining reliability for the weaker cells that require more frequent refreshes.
Solution Approach 2:
The patent applies local quality by providing enhanced refresh operations specifically to first memory cells with weaker retention characteristics, while using standard refresh operations for second memory cells with stronger retention. This localized approach ensures that only the cells needing additional attention receive extra refresh resources, optimizing die size.
3Reliability
If traditional refresh operations are used for all memory cells, then refresh parameters are met, but refresh overhead increases
Solution Approach 1:
The patent segments memory cells into two categories: first memory cells with weaker retention characteristics and second memory cells with stronger retention characteristics. This segmentation allows different refresh strategies to be applied to each group, reducing overall refresh overhead while maintaining reliability for the weaker cells that require more frequent refreshes.
Solution Approach 2:
The patent applies local quality by providing enhanced refresh operations specifically to first memory cells with weaker retention characteristics, while using standard refresh operations for second memory cells with stronger retention. This localized approach ensures that only the cells needing additional attention receive extra refresh resources, optimizing refresh overhead.
Data Source
AI summary
Methods, systems, and devices for retention aware refresh operations are described. A memory system supporting retention aware refresh may involve a first counter associated with a first set of memory cells and a second set of memory cells, and a second counter associated with the second set of memory cells, where the second set of memory cells may be associated with a set of memory elements. The memory system may further include a memory element selection component configured to select at least a subset of the second set of memory cells based on the second counter, and an address selection component configured to select a first address output by the first counter or a second address output by the memory element selection component for a refresh operation. Multiple second sets of memory cells, memory element selection components, and address selection components also may be included.


