Dynamic Buffer Memory Allocation for Flash Storage
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Flash memory devices face inefficiencies in data storage due to limited buffer memory capacity, leading to low map hit ratios and inefficient use of storage areas, especially when static separation of data and map areas restricts dynamic allocation based on read operation modes.
Innovation Solution
A semiconductor storage device with a controller that dynamically allocates memory space between a data area and a map area in the buffer memory, adapting sizes according to user data and read operation modes to enhance map hit ratios and optimize storage capacity utilization.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the buffer memory is statically separated into fixed data area and map area, then the structure is simple and stable, but the storage efficiency is low and map hit ratio decreases when read operation modes change
Solution Approach 1:
The patent applies dynamics by making the buffer memory area allocation movable and adjustable. The data area and map area boundaries are no longer fixed but can be dynamically shifted based on read operation modes. When sequential read is detected, the data area expands; when random read is detected, the map area expands. This dynamic allocation resolves the contradiction by allowing the structure to adapt to different operational requirements, thereby maintaining structural simplicity while improving storage efficiency and map hit ratio.
2Quantity of substance
If the buffer memory capacity is increased, then the storage capacity utilization improves, but the device complexity and cost increase
Solution Approach 1:
The patent applies parameter changes by modifying the allocation parameters of the buffer memory areas based on operational conditions. Instead of increasing the total buffer memory capacity, the system changes the distribution parameters of existing capacity between data area and map area. The controller adjusts area sizes by comparing read operation modes (sequential vs. random) and reallocating buffer space accordingly. This resolves the contradiction by achieving better storage capacity utilization through parameter optimization rather than capacity expansion, thereby avoiding increased device complexity and cost.
3Quantity of substance
If the data area size is increased to store more user data, then the data storage capacity improves, but the map area size decreases leading to lower map hit ratio
Solution Approach 1:
The patent applies dynamics by making the data area and map area sizes variable rather than fixed. The system dynamically adjusts the size of each area based on the detected read operation mode. During sequential read operations, the data area is expanded to maximize data storage capacity. During random read operations, the map area is expanded to maximize map hit ratio. This dynamic resizing resolves the contradiction by allowing both data storage capacity and map hit ratio to be optimized at different times based on operational needs.
Solution Approach 2:
The patent applies parameter changes by modifying the size parameters of data area and map area based on operational conditions. The controller changes the allocation parameters (area sizes) according to read operation modes detected through comparison of read addresses. This parameter adjustment allows the system to prioritize data storage capacity when needed while maintaining map hit ratio when required, resolving the contradiction through conditional parameter optimization.
4Productivity
If the map area size is increased to improve map hit ratio, then the address mapping efficiency improves, but the data area size decreases limiting storage capacity
Solution Approach 1:
The patent applies dynamics by making the map area size variable and adjustable based on operational requirements. Instead of maintaining a fixed map area size, the system dynamically expands the map area when random read operations are detected to improve address mapping efficiency and map hit ratio. Conversely, during sequential read operations, the map area is reduced to allow larger data area for maximum storage capacity. This dynamic adjustment resolves the contradiction by allowing address mapping efficiency to be optimized when needed without permanently sacrificing data storage capacity.
Data Source
AI summary
A method of operating a semiconductor storage device is provided. A memory space of a buffer memory is allocated into a data area for storing user data and a map area for storing map data. The user data and the map data are read from a nonvolatile memory. A size of the user data to be stored in the data are compared with a size of the data area. The size of the data area and the size of the map area are adaptively varied according to the comparison result.


