Dynamic Super Blocks for Recycling Grown Bad NVM Blocks
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional methods for handling bad blocks in non-volatile memory (NVM) lead to premature reduction in programmable blocks and increased cycling, shortening the lifespan of NVM by retiring entire blocks instead of recycling usable memory locations.
Innovation Solution
Generating dynamic super blocks from subsets of memory locations within bad blocks, selected based on reliability measurements, to form new, usable blocks that can extend the lifespan of NVM by recycling otherwise retired memory portions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If entire bad blocks are retired, then data reliability is maintained, but the pool of programmable blocks shrinks and lifespan is reduced
Solution Approach 1:
The patent divides a bad block into multiple segments (good pages and bad pages) based on page-level reliability assessment. Instead of retiring the entire block, only the defective pages are identified and isolated, allowing the remaining good pages to be reused. This segmentation resolves the contradiction by maintaining data reliability through error isolation while extending NVM lifespan through selective page recycling.
Solution Approach 2:
The patent applies local quality assessment by evaluating each page within a block individually rather than treating the entire block uniformly. Pages are classified as good or bad based on local error characteristics, and different management strategies are applied to different pages. This allows reliable pages to continue serving data while defective pages are retired, thus preserving overall block usability and extending NVM lifespan without compromising data reliability.
2Reliability
If entire bad blocks are retired, then data integrity is protected, but cycling of remaining blocks increases
Solution Approach 1:
By segmenting the block into good and bad pages, the patent enables continued use of reliable pages, thereby reducing the need to retire entire blocks. This segmentation maintains data integrity through selective page management while reducing the cycling frequency of remaining blocks, as more capacity remains available for reuse.
Solution Approach 2:
The patent discards only the defective pages within a block while recovering and continuing to use the good pages. This selective discarding and recovery approach protects data integrity by isolating errors to specific pages while minimizing the impact on overall block availability and reducing the cycling rate of functional blocks.
3Quantity of substance
If subsets of memory locations from bad blocks are recycled, then programmable block pool is expanded, but complexity of block management increases
Solution Approach 1:
The patent uses segmentation to divide blocks into good and bad pages, creating a structured approach to managing recycled memory locations. This segmentation simplifies the management complexity by providing clear categorization rules and systematic procedures for identifying, isolating, and reusing good pages, thereby expanding the programmable block pool without proportionally increasing management complexity.
Solution Approach 2:
The patent performs preliminary assessment and classification of pages within blocks before recycling. By pre-identifying good and bad pages through reliability testing and categorization, the system prepares the memory structure in advance for efficient recycling. This preliminary action reduces subsequent management complexity by establishing clear boundaries and usage rules before the recycling process begins.
4Duration of action of stationary object
If dynamic super blocks are generated from bad blocks, then NVM lifespan is extended, but measurement precision requirements increase
Solution Approach 1:
The patent applies segmentation by dividing blocks into page-level units for individual reliability assessment. This granular segmentation enables precise measurement of reliability at the page level, allowing the system to accurately identify which pages can be safely recycled. The segmentation approach extends NVM lifespan by maximizing reusable capacity while managing measurement precision through systematic page-level evaluation.
Solution Approach 2:
The patent changes the measurement parameter from block-level reliability to page-level reliability. By shifting the assessment granularity from entire blocks to individual pages, the system achieves more precise reliability measurements that enable finer-grained recycling decisions. This parameter change extends NVM lifespan by identifying more reusable memory locations while maintaining acceptable measurement precision through page-level analysis.
Data Source
AI summary
Systems and methods are disclosed for generating dynamic super blocks from one or more grown bad blocks of a non-volatile memory (“NVM”). In some embodiments, a dynamic super block can be formed by striping together a subset of memory locations of grown bad blocks from one or more dies of a NVM. The subset of memory locations may be selected based on at least one reliability measurement of the subset of memory locations. In some embodiments, in response to detecting one or more access failures in a portion of the dynamic super block, the NVM interface can retire at least a portion of the dynamic super block. In some embodiments, the NVM interface can reconstruct a new dynamic super block from the dynamic super block by progressively increasing the size of the new dynamic super block.