Stuck-at Fault Correction in Phase Change Memory via Redundant Bit Encoding
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Phase change memory (PCM) devices experience high error rates due to degradation, particularly stuck-at faults, which are not effectively addressed by existing error correction methods designed for random errors.
Innovation Solution
A data storage system that includes a control circuit generating redundant bits to indicate bit positions and transform data bits to correct stuck-at faults, allowing for accurate storage and retrieval of data in memory cells with stuck-at faults, using techniques such as combinatorial encoding and binary tree algorithms.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If error correction encoders are used to correct random errors, then data reliability is improved, but the system cannot effectively correct stuck-at faults caused by degradation
Solution Approach 1:
The patent changes the error correction approach by detecting stuck-at faults through read operations and modifying the encoding scheme based on the detected fault pattern. The control circuit generates encoded data bits with modified Hamming weights to accommodate stuck-at faults, transforming the correction method from generic random error correction to targeted fault-specific correction.
Solution Approach 2:
The system implements feedback by performing read operations to detect stuck-at faults and using this information to adjust the encoding scheme for subsequent write operations. The control circuit continuously monitors memory cell states and adapts the encoding strategy based on detected faults, creating a closed-loop error correction system.
2Manufacturing precision
If redundant bits are generated to indicate bit positions of stuck-at faults, then data storage accuracy is improved, but device complexity increases
Solution Approach 1:
The patent segments the error correction process into distinct phases: detection phase (read operations to identify stuck-at faults), encoding phase (generating encoded data bits with modified Hamming weights), and storage phase (writing encoded data to memory). This segmentation allows the control circuit to manage complexity through structured, modular operations.
Solution Approach 2:
The control circuit performs multiple functions: it reads data to detect stuck-at faults, generates redundant bits indicating fault positions, creates encoded data bits with modified Hamming weights, and writes data to memory. This multi-functionality consolidates error detection, encoding, and correction capabilities into a single control circuit, managing complexity through integrated design.
3Measurement precision
If encoded data bits are generated to match digital values of stuck-at faults, then data retrieval accuracy is improved, but operational time increases
Solution Approach 1:
The system performs preliminary detection of stuck-at faults through read operations before the actual data storage operation. By identifying and characterizing stuck-at faults in advance, the control circuit can pre-generate appropriate encoded data bits with modified Hamming weights, reducing the time needed during subsequent write operations.
Solution Approach 2:
The patent maintains continuous operation by seamlessly integrating fault detection and encoded data generation into the normal write workflow. The control circuit continuously monitors memory cell states and maintains an updated mapping of stuck-at faults, allowing rapid generation of encoded data bits without interrupting the data storage process.
Data Source
AI summary
A data storage system includes a memory circuit comprising memory cells and a control circuit. The control circuit generates a first set of redundant bits indicating bit positions of the memory cells having stuck-at faults in response to a first write operation if a first rate of the stuck-at faults in the memory cells is greater than a first threshold. The control circuit is operable to encode data bits to generate encoded data bits and a second set of redundant bits that indicate a transformation performed on the data bits to generate the encoded data bits in response to a second write operation if a second rate of stuck-at faults in the memory cells is greater than a second threshold. The encoded data bits stored in the memory cells having the stuck-at faults match digital values of corresponding ones of the stuck-at faults.