Selective Memory Compression for Mobile App Launch Bottlenecks

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing memory management systems face challenges in efficiently utilizing memory compression methods, which can lead to insufficient memory space and inefficient use of existing memory compression technologies, which can degrade system performance and increase the cost of manufacturing and the cost of manufacturing.

Innovation Solution

A method and apparatus for selectively compressing data in electronic devices based on system demands, using a CPU or hardware accelerator to improve memory utilization and reduce the need for additional memory, thereby enhancing compression performance and reducing manufacturing costs.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Quantity of substance

If memory compression is applied to secure available memory space, then memory storage capacity is improved, but service rate deteriorates due to compression/decompression overhead

Engineering Contradiction:
Improvememory storage capacityVSAvoidservice rate
Core Design Contradiction:
Quantity of substanceVSProductivity

Solution Approach 1:

The patent applies preliminary action by pre-compressing memory data before it is needed, and pre-loading decompression algorithms and data structures into fast memory. This preparation work is done in advance during low-utilization periods, so that when compression is actually needed, the system can quickly switch to compressed mode without significant performance penalty. The decompression buffers and translation lookaside buffers (TLB) are pre-configured to minimize latency.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent implements dynamics by creating a hybrid memory system that dynamically switches between compressed and uncompressed states based on workload characteristics, access patterns, and memory pressure. The system can adjust compression ratios, switch between different compression algorithms, and move data between compressed and uncompressed memory regions in real-time. This dynamic adaptation allows the system to optimize for both storage capacity and service rate depending on current system conditions.

Inventive Principle:
Principle #15Dynamics

2Quantity of substance

If swapping is used to secure available memory space, then memory capacity is improved, but access speed deteriorates due to slow disk access

Engineering Contradiction:
Improvememory capacityVSAvoidaccess speed
Core Design Contradiction:
Quantity of substanceVSSpeed

Solution Approach 1:

The patent introduces an intermediary compressed memory layer between the physical memory and the disk storage system. Instead of directly swapping data between memory and disk, the system compresses data in memory before potential swap operations, reducing the amount of data that needs to be transferred to disk. The compression layer acts as a mediator that transforms data representation to minimize I/O operations and transfer volumes, thereby maintaining faster access speeds while effectively increasing usable memory capacity.

Inventive Principle:
Principle #24Intermediary (Mediator)

3Quantity of substance

If additional memory is adopted to meet application demands, then memory capacity is improved, but manufacturing cost increases

Engineering Contradiction:
Improvememory capacityVSAvoidmanufacturing cost
Core Design Contradiction:
Quantity of substanceVSEase of manufacture

Solution Approach 1:

The patent applies parameter changes by transforming the physical state of memory data from uncompressed to compressed form, effectively changing the density parameter of stored information. By applying compression algorithms, the system achieves higher effective storage capacity from the same physical memory hardware. This parameter transformation allows the system to meet growing application memory demands without proportionally increasing physical memory hardware, thereby reducing manufacturing costs while maintaining adequate memory capacity.

Inventive Principle:
Principle #35Parameter changes

Data Source

PatentEP4145295B1Memory compression method of electronic device and apparatus thereof
Publication Date: 2025.12.17 SAMSUNG ELECTRONICS CO LTD
  • EP4145295B1 patent drawingFigure 1A
  • EP4145295B1 patent drawingFigure 1B
  • EP4145295B1 patent drawingFigure 1C

AI summary

Disclosed are a memory compression method of an electronic device and an apparatus thereof. The method for compressing memory in an electronic device may include: detecting a request for executing the first application; determining whether or not the memory compression is required for the execution of the first application; when the memory compression is required, compressing the memory corresponding to an application in progress in the background of the electronic device; and executing the first application.