Nonvolatile Memory Compaction Using Valid Data Relocation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing nonvolatile memory systems face inefficiencies in data compaction processes, leading to fragmented data storage and reduced performance due to the inability to effectively manage valid and invalid data within memory blocks.
Innovation Solution
A nonvolatile memory system with a command processing unit that performs data compaction by determining data validity and relocating valid data to new blocks while managing metadata for efficient block management, utilizing error correction and parallel processing across multiple channels.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If data compaction is performed by reading all data from memory blocks and determining validity, then data compaction speed is improved, but the complexity of managing valid and invalid data increases
Solution Approach 1:
The patent divides the memory block into multiple pages, each with its own validity information. This segmentation allows the system to manage validity at a finer granularity, improving compaction speed by processing smaller units independently while reducing the overall complexity through structured organization of validity data.
Solution Approach 2:
The patent introduces a validity determination unit as an intermediary component that manages the complexity of determining data validity. This dedicated unit processes validity information for each page, separating the complexity management function from the main compaction process and enabling faster execution.
2Productivity
If valid data is relocated to new blocks during compaction, then block utilization is improved, but data fragmentation increases
Solution Approach 1:
The patent performs preliminary actions by determining validity for all pages in a block before initiating data relocation. This preliminary validity determination allows the system to plan the compaction process in advance, relocating only valid data to optimal blocks while maintaining composition stability through structured relocation protocols.
Solution Approach 2:
The patent implements discarding invalid data and recovering valid data to new blocks. By systematically discarding only the invalid portions and recovering valid data through controlled relocation, the system improves block utilization while managing fragmentation through metadata tracking of valid data regions.
3Reliability
If error correction is applied during data compaction, then data reliability is improved, but processing time increases
Solution Approach 1:
The patent applies partial error correction by focusing on error correction only for pages that are determined to be valid during the compaction process. This partial action approach improves reliability for the data that will be relocated while reducing processing time by avoiding unnecessary error correction operations on invalid data.
Solution Approach 2:
The patent maintains continuity of useful action by integrating error correction into the ongoing compaction process rather than performing it as a separate sequential step. The validity determination and error correction operations proceed in parallel where possible, ensuring continuous productive action while maintaining data reliability.
Data Source
AI summary
According to one embodiment, a nonvolatile memory includes a memory chip and a command processing unit. The command processing unit stores data read from a first position of the memory chip in a memory when a first command for compaction is received from a controller, transmits validity determination information used for determining whether or not the data read from the first position is valid to the controller, and writes valid data of the data stored in the memory to a second position of the memory chip when a second command for the compaction and validity identification information that identifies the valid data are received from the controller.