Memory Controller Compression for Cold Data Big-Data Storage
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current memory systems face challenges in efficiently storing and managing large-capacity data, particularly in portable electronic devices, where existing technologies do not effectively utilize compression and decompression methods to optimize storage and retrieval processes.
Innovation Solution
A controller with a selection block to identify cold data, a compression block to divide and compress data in parallel, and an arbitration block to packetize and store data efficiently, along with a method for decompressing and retrieving data based on address information, enabling efficient storage and loading of large-capacity data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If data is stored without compression in memory systems, then data access speed is maintained, but storage capacity utilization is insufficient and storage efficiency deteriorates
Solution Approach 1:
The patent applies compression algorithms to change the physical state of data from uncompressed to compressed form, thereby reducing storage space requirements. The controller dynamically adjusts compression parameters based on data types and access patterns, achieving better storage capacity utilization without significantly impacting access speed for cold data
Solution Approach 2:
The patent segments data into hot data and cold data categories, applying different storage strategies to each. Cold data is compressed and stored in memory devices, while hot data is kept in buffer memory for fast access. This segmentation allows the system to optimize storage efficiency for less frequently accessed data while maintaining fast access for frequently accessed data
2Quantity of substance
If compression is applied to all data, then storage efficiency is improved, but processing time and system complexity increase
Solution Approach 1:
The patent applies compression selectively rather than uniformly across all data. The controller analyzes data characteristics and applies compression algorithms only to cold data that benefits from compression, while leaving hot data uncompressed for fast access. This local quality approach optimizes storage efficiency for specific data types without unnecessarily increasing system complexity for all data processing paths
3Quantity of substance
If cold data is identified and compressed, then storage capacity is optimized, but additional processing overhead is introduced
Solution Approach 1:
The patent implements preliminary classification of data into hot and cold categories upon receipt. Cold data is identified early and routed directly to compression and storage, while hot data is buffered for immediate access. This preliminary action prevents unnecessary compression processing for hot data, reducing overall processing overhead while still achieving storage capacity optimization for cold data
Data Source
AI summary
In accordance with an embodiment, a controller may be provided. The controller may include a selection block configured to select cold data among write data. The controller may include a compression block configured to generate a plurality of unit data by dividing the cold data according to a predetermined size, assign each of the unit data to each of a plurality of channels, and compressing in parallel each of the unit data to generate compressed data. The controller may include an arbitration block configured to generate a plurality of packet data by packetizing each of the compressed data, and outputting the packet data.