Memory Controller Page Boundary Search
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Memory systems face challenges in efficiently searching for and restoring the state of pages after a sudden power-off (SPO), particularly in identifying the boundary between program and erase states in open memory blocks, which affects data integrity and system reliability.
Innovation Solution
A memory system and method that employs a controller to non-sequentially select pages using binary and linear searches to identify the boundary page between program and erase states by classifying memory blocks and adjusting search ranges, ensuring accurate state checking and efficient data recovery post-power restoration.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If sequential checking of all pages is performed after sudden power-off, then data integrity is ensured, but recovery time increases significantly
Solution Approach 1:
The patent divides the memory block into multiple segments or regions, and performs parallel checking operations on different segments simultaneously. This segmentation allows the system to maintain comprehensive verification (data integrity) while reducing the sequential time required by enabling concurrent processing across divided portions of the memory block.
Solution Approach 2:
The patent implements preliminary marking or tagging of pages during normal operation, so that after sudden power-off, the recovery process can quickly identify which pages need checking without examining every page sequentially. This preliminary action prepares the system in advance, allowing faster recovery while ensuring data integrity through targeted verification.
2Measurement precision
If comprehensive page state checking is performed, then accurate boundary identification is achieved, but processing complexity increases
Solution Approach 1:
The patent applies partial checking strategies where not all pages are examined with the same thoroughness. Instead, it uses a combination of quick checks on some pages and detailed verification on others, achieving accurate boundary identification through selective processing rather than uniform comprehensive checking, thereby reducing overall processing complexity.
Solution Approach 2:
The patent introduces intermediary data structures or helper variables that facilitate boundary identification without requiring complex processing logic. These intermediaries act as mediators between the raw page states and the final boundary determination, simplifying the processing complexity while maintaining measurement precision.
3Productivity
If binary search is used for non-sequential page selection, then search efficiency improves, but implementation complexity increases
Solution Approach 1:
The patent divides the page range into segments and applies binary search principles within each segment or uses segmented approaches to simplify the overall binary search implementation. This segmentation reduces implementation complexity by breaking down the complex search algorithm into manageable, repetitive units while maintaining search efficiency.
Solution Approach 2:
The patent uses simplified copies or approximations of the binary search logic in certain contexts, or replicates the search pattern across multiple pages with minor variations. This copying approach reduces implementation complexity by reusing the same basic search template rather than implementing complex conditional logic for each case, while still achieving high search efficiency.
Data Source
AI summary
A memory system may include a memory device including a plurality of memory blocks each memory block including a plurality of pages; and a controller suitable for non-sequentially selecting some pages among a plurality of pages included in an open block among the plurality of blocks, checking a program state or an erase state of each of the selected pages, and searching for a boundary page between the program state pages and the erase state pages among the plurality of pages.