Flexible Flash Translation Mapping for Compressed SSD Pages

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing data storage devices face limitations in storing more user data due to limited internal resources and require additional computing power and memory for data compression, leading to inconsistent address sizes and increased complexity.

Innovation Solution

A flexible dynamic granularity mapping system, known as F-FTL, is implemented in SSDs to manage logical and physical addresses efficiently, allowing seamless data compression without additional software or hardware modifications, reducing memory requirements and maintaining performance.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Quantity of substance

If data compression is implemented in existing storage devices, then storage capacity is improved, but device complexity and memory requirements increase

Engineering Contradiction:
Improvestorage capacityVSAvoiddevice complexity
Core Design Contradiction:
Quantity of substanceVSDevice complexity

Solution Approach 1:

The system performs data compression automatically at the storage device level without requiring external software or hardware modifications. The compression function is integrated into the storage device's native operations, allowing it to serve itself and achieve space efficiency without adding external complexity

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The storage device's controller is designed to handle multiple functions including compression, decompression, and address mapping within a single integrated system. This multi-functionality allows the device to improve storage capacity while managing complexity through unified control rather than separate dedicated components

Inventive Principle:
Principle #6Universality (Multi-functionality)

2Quantity of substance

If data compression is implemented in existing storage devices, then storage capacity is improved, but additional computing power and memory are required

Engineering Contradiction:
Improvestorage capacityVSAvoidcomputing power and memory
Core Design Contradiction:
Quantity of substanceVSUse of energy by moving object

Solution Approach 1:

The storage device utilizes its own integrated controller resources to perform compression operations, leveraging existing computing power and memory within the device rather than requiring additional external resources. The system serves its own compression needs through native controller capabilities

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The system dynamically adjusts compression parameters and data granularity based on available resources and data characteristics. By changing compression intensity and data organization parameters, the system achieves improved storage capacity while adapting computing resource usage to match available capacity

Inventive Principle:
Principle #35Parameter changes

3Quantity of substance

If flexible dynamic granularity mapping is implemented, then storage efficiency is improved, but address management complexity increases

Engineering Contradiction:
Improvestorage efficiencyVSAvoidaddress management complexity
Core Design Contradiction:
Quantity of substanceVSDevice complexity

Solution Approach 1:

The address space is divided into logical and physical address segments that can be independently managed. The flexible mapper segments the mapping process into discrete logical-to-physical transformations, allowing efficient storage utilization while managing address complexity through structured segmentation rather than monolithic address management

Inventive Principle:
Principle #1Segmentation

Data Source

PatentUS20260044273A1Flash translation apparatus and storage method
Publication Date: 2026.02.12 SAMSUNG ELECTRONICS CO LTD
  • US20260044273A1 patent drawing
  • US20260044273A1 patent drawing
  • US20260044273A1 patent drawing

AI summary

A storage device is provided. The storage device includes: a nonvolatile memory device configured to provide a physical address space; and at least one processor configured to implement: a flexible mapper configured to: obtain a size of compressed data in a logical page of a logical address space, the compressed data being obtained by compressing raw data; and determine, based on the size of the compressed data, a number of physical pages of the physical address space for storing the compressed data; a physical page manager configured to allocate physical pages corresponding to the number of physical pages; and a write controller configured to write data to the physical pages allocated by the physical page manager.