Historical Soft-Information Decoding for Non-Volatile Storage

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing data communication and storage systems face inefficiencies in error correction due to the computational complexity of error-correcting codes, such as Hamming, Reed-Solomon, and LDPC codes, which require improvements in decoding processes, especially in non-volatile storage devices.

Innovation Solution

A method that utilizes historical soft information from previous decoding operations to enhance decoding efficiency by retrieving and updating reliability information for data chunks, employing a storage system controller with a decoder, soft information fetcher, and generator to improve error correction in non-volatile storage systems.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If traditional error-correcting codes (Hamming, Reed-Solomon, LDPC) are used for data correction, then data reliability is improved, but computational complexity increases

Engineering Contradiction:
Improvedata reliabilityVSAvoidcomputational complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The system performs preliminary actions by collecting and storing soft information from previous decoding operations before actual decoding is needed. This historical data is cached in advance, allowing the decoder to leverage pre-computed reliability information and reduce real-time computational burden while maintaining high data reliability through informed decoding decisions

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system implements feedback by continuously collecting soft information from decoding operations and using this historical data to improve future decoding performance. The cached soft information from previous operations feeds back into the decoding process, creating a self-improving system that reduces computational complexity while maintaining reliability through iterative learning from past decoding outcomes

Inventive Principle:
Principle #23Feedback

2Measurement precision

If soft information from previous decoding operations is collected and stored, then decoding accuracy is improved, but memory usage increases

Engineering Contradiction:
Improvedecoding accuracyVSAvoidmemory usage
Core Design Contradiction:
Measurement precisionVSQuantity of substance

Solution Approach 1:

The system extracts only the essential soft information from previous decoding operations that is most useful for improving decoding accuracy. By selectively caching only the relevant reliability data rather than storing complete decoding states, the system achieves high decoding accuracy while minimizing memory consumption through targeted extraction of useful information

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The system applies local quality by storing soft information at the granularity of individual data chunks or blocks rather than entire datasets. This localized storage approach allows the system to maintain high decoding accuracy for specific problematic areas while keeping overall memory usage manageable by only caching information where it provides the most benefit

Inventive Principle:
Principle #3Local quality

3Productivity

If computational overhead is reduced in decoding processes, then processing speed is improved, but decoding reliability may deteriorate

Engineering Contradiction:
Improveprocessing speedVSAvoiddecoding reliability
Core Design Contradiction:
ProductivityVSReliability

Solution Approach 1:

The system implements self-service by automatically generating and caching soft information from its own decoding operations. This self-collected historical data serves the system's own future decoding needs, enabling faster processing through reduced computational overhead while maintaining reliability through the use of internally-generated, context-aware soft information that is specifically tailored to the system's own data characteristics

Inventive Principle:
Principle #25Self-service

Data Source

PatentUS11159182B1Systems and methods for decoding error correcting codes with historical decoding information
Publication Date: 2021.10.26 INNOGRIT TECH CO LTD
  • US11159182B1 patent drawing
  • US11159182B1 patent drawing
  • US11159182B1 patent drawing

AI summary

Systems and methods are provided for decoding data read from non-volatile storage devices. A method may comprise receiving a chunk of data read from a physical location of a non-volatile storage device and searching a memory for soft information associated with the physical location using a unique identifier associated with the physical location. The soft information may be generated from one or more previous decoding processes on previous data from the physical location. The method may further comprise retrieving the soft information identified by the unique identifier associated with the physical location from the memory, decoding the chunk of data with the soft information indicating reliability of bits in the chunk of data and updating the soft information with decoding information generated during the decoding.