Storage Compression Control Using Start Data Unit Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing storage devices face challenges in efficiently storing large amounts of data, particularly for applications like artificial intelligence and machine learning, due to limitations in data compression efficiency.
Innovation Solution
A storage device that selectively applies different compression algorithms to different parts of data, using a start data unit to determine an optimal algorithm, thereby increasing the overall compression ratio and improving storage efficiency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If a single compression algorithm is applied to all data units, then the device complexity is reduced, but the compression ratio of the entire data decreases
Solution Approach 1:
The patent divides the data into multiple data units and applies different compression algorithms to different segments based on their characteristics. The controller selects appropriate compression algorithms from a plurality of candidate algorithms for each data unit or group of data units, enabling optimized compression ratios for diverse data types while maintaining manageable system complexity through structured segmentation.
2Loss of substance
If multiple compression algorithms are selectively applied to different data units, then the compression ratio of the entire data increases, but the device complexity increases
Solution Approach 1:
The patent performs preliminary classification of data units using start data units to determine which compression algorithms to apply to subsequent data units. By analyzing the characteristics of start data units and pre-determining the compression algorithm selection, the system optimizes compression ratios for entire groups of data units without requiring complex real-time analysis of each individual data unit, thus balancing compression efficiency with device complexity.
3Quantity of substance
If data is compressed to increase storage efficiency, then the storage capacity for large data volumes improves, but the processing time may increase
Solution Approach 1:
The patent applies compression selectively to data units that benefit most from compression, rather than compressing all data uniformly. By identifying and compressing only those data units where compression is effective (based on data characteristics analyzed from start data units), the system achieves improved storage efficiency while minimizing the additional processing time that would result from compressing all data regardless of compressibility.
Data Source
AI summary
A storage device may include a memory and a controller. The controller may compress a plurality of data units inputted from a host into a plurality of compressed data units, and may store the plurality of compressed data units in the memory. The controller may determine a first compression algorithm among a plurality of candidate compression algorithms on the basis of a start data unit which is inputted first among the plurality of data units, may compress N number of first data units, which are inputted first among the plurality of data units, into M number of first compressed data units using the first compression algorithm, and may store the M number of first compressed data units in the memory.