Soft Data Generation for Low-Latency Flash Memory Decoding
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Data in solid state storage devices decays over time, requiring enhanced error correction capabilities, which increases access latency, necessitating advanced systems and methods to maintain data integrity.
Innovation Solution
The implementation of a data processing system that includes a solid state memory, a data de-randomizer circuit, a soft data generation circuit, and a data decoder circuit, utilizing a scramble compensating extended lookup table to de-randomize read data and apply decoding algorithms to yield accurate outputs, thereby compensating for internal or external randomization and improving error correction without increasing latency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If enhanced error correction circuitry is employed to correct additional errors, then data integrity is improved, but access latency increases
Solution Approach 1:
The patent applies preliminary action by performing multiple reads with different reference values before the actual data access is needed. This generates soft data and populates lookup tables in advance, so that when data needs to be retrieved, the error correction can proceed faster using pre-computed information rather than performing all reads at the moment of access.
Solution Approach 2:
The patent implements dynamics by making the read process adaptive - it performs multiple reads with different reference values and uses dynamic programming/lookup tables to determine the most likely original data values. This dynamic approach allows the system to adjust to varying error conditions while maintaining fast access times through cached results.
2Reliability
If multiple reads with different reference values are performed to generate soft data, then error correction capability is improved, but read time increases
Solution Approach 1:
The system performs the multiple reads with different reference values as a preliminary step before actual data access. The results are stored in lookup tables that can be quickly queried during normal operations, converting a time-consuming process into a fast lookup operation.
Solution Approach 2:
The patent creates copies of the data by reading the same memory location multiple times with different reference values. These copies are then processed to generate soft data that provides richer information for error correction, while the lookup table stores pre-processed copies that speed up subsequent accesses.
3Measurement precision
If a scramble compensating extended lookup table is used to de-randomize data, then data accuracy is improved, but memory resources increase
Solution Approach 1:
The patent applies local quality by creating specialized lookup tables for specific purposes (de-randomization, soft data generation) rather than using general-purpose memory. Each lookup table is optimized for its specific function and can be relatively small in size, allowing the system to maintain high data accuracy without requiring large amounts of additional memory resources.
Solution Approach 2:
The lookup tables serve multiple functions: they store soft data for error correction, compensate for scrambling/randomization effects, and provide pre-computed results for multiple reads. This multi-functionality reduces the need for separate memory structures for each purpose, optimizing the use of memory resources.
Data Source
AI summary
Systems and method relating generally to solid state memory, and more particularly to systems and methods for generated data from a solid state memory. A data processing system includes a solid state memory device, a soft data generation circuit operable to receive multiple instances of an element of a read data set accessed from the solid state memory device, and access a scramble compensating extended look up table using the multiple instances of the element to receive corresponding soft data, and a data decoder circuit operable to yield a decoded output from the soft data.