Data Storage Bit-Width Selection With Blockwise Differentials

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

The current method of storing effective bit numbers of data occupies a larger storage bit width, especially in computer systems handling large amounts of data.

Innovation Solution

The method involves dividing data into blocks, determining effective bit numbers within each block, and performing differential calculations on sub-blocks to determine optimal storage bit widths for the differential values of these bit numbers.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of manufacture

If effective bit numbers are stored by allocating bits according to their storage bit width, then the storage method is simple and direct, but a larger storage bit width is occupied

Engineering Contradiction:
Improvestorage method simplicityVSAvoidstorage bit width
Core Design Contradiction:
Ease of manufactureVSQuantity of substance

Solution Approach 1:

The patent changes the storage parameter from storing absolute effective bit numbers to storing differential values between adjacent effective bit numbers. This parameter transformation reduces the storage bit width required, as differential values typically have smaller magnitudes and can be represented with fewer bits compared to the original effective bit numbers.

Inventive Principle:
Principle #35Parameter changes

Solution Approach 2:

The patent segments the storage approach by dividing data into blocks and processing effective bit numbers in groups. By segmenting the storage problem into block-level differential calculations, the system achieves more efficient bit width utilization while maintaining the simplicity of the storage method.

Inventive Principle:
Principle #1Segmentation

2Reliability

If a larger storage bit width is allocated to store effective bit numbers, then all effective bit numbers can be stored without loss, but storage efficiency decreases

Engineering Contradiction:
Improvestorage accuracyVSAvoidstorage efficiency
Core Design Contradiction:
ReliabilityVSProductivity

Solution Approach 1:

The patent transforms the storage parameter from absolute values to differential values, which preserves the information content while reducing the bit width required. This parameter change maintains storage accuracy because the differential values can be used to reconstruct the original effective bit numbers, while simultaneously improving storage efficiency by reducing the allocated bit width.

Inventive Principle:
Principle #35Parameter changes

3Productivity

If differential calculation is performed on effective bit numbers to reduce storage bit width, then storage efficiency is improved, but the storage method becomes more complex

Engineering Contradiction:
Improvestorage efficiencyVSAvoidstorage method complexity
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The patent applies segmentation by dividing data into blocks and performing differential calculations at the block level. This segmentation approach reduces the overall complexity compared to processing individual effective bit numbers, as it allows for batch processing and reduces the frequency of differential calculations, thereby improving storage efficiency while keeping the method manageable.

Inventive Principle:
Principle #1Segmentation

Data Source

PatentUS12430240B2Method and apparatus for determining data storage bit width, and method for storing index data
Publication Date: 2025.09.30 CALTERAH SEMICON TECH (SHANGHAI) CO LTD
  • US12430240B2 patent drawing
  • US12430240B2 patent drawing

AI summary

A method and apparatus for determining a data storage bit width and a method for storing exponential data. The method for determining the data storage bit width includes: acquiring data to be stored, the number of which is at least 4; dividing the data into blocks according to a preset number 2n, n is an integer greater than or equal to 2; determining effective bit numbers and a value of a maximum effective bit number in a block; dividing data in the block equally into a first sub-block and a second sub-block, acquiring effective bit numbers in first and second sub-blocks; performing a differential calculation on effective bit numbers in first and second sub-blocks to obtain an effective differential value; determining a storage bit width for storing effective differential value according to a preset storage bit width interval to which the value of maximum effective bit number belongs.