Memory Cell Programming With Temporary Parity Buffering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional memory systems face challenges in programming memory blocks with defects, leading to data loss and increased uncorrectable bit error rates (UBER) due to the tradeoff between buffer size for defect coverage and concurrent programming, resulting in inefficiencies and penalties.
Innovation Solution
Implementing temporary parity data buffering during multiple-pass programming to reduce the required buffer size while maintaining data integrity, using less space than user data and allowing earlier release of buffer resources, thus minimizing UBER without excessive overprovisioning.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If buffer size is increased to cover defects and enable concurrent programming, then data integrity and reliability are improved, but device complexity and overprovisioning penalties increase
Solution Approach 1:
The buffer is segmented into two distinct parts: a first buffer for storing user data and a second buffer for storing parity data. This segmentation allows the system to maintain data integrity through parity checking while using smaller, more manageable buffer sizes compared to a single large buffer that would be needed for full defect coverage.
Solution Approach 2:
Parity data acts as an intermediary element between the user data and the defect coverage requirement. Instead of directly storing redundant user data copies in the buffer, the system uses parity data (XOR combinations of user data) as a mediator that provides error detection and correction capabilities with reduced buffer space requirements.
2Reliability
If buffer size is increased to maintain data integrity during programming, then uncorrectable bit error rate is reduced, but overprovisioning penalties increase
Solution Approach 1:
The system changes the parameter of data representation in the buffer by storing parity data instead of full user data copies. This parameter change reduces the quantity of data that needs to be buffered while maintaining the ability to detect and correct errors, thereby reducing UBER without requiring excessive buffer blocks.
Solution Approach 2:
Instead of copying entire user data blocks to protect against defects, the system creates compact parity data copies that represent the user data. These parity copies take up less space in the buffer but still enable error detection and correction, reducing the number of buffer blocks needed.
3Reliability
If full user data is buffered for defect coverage, then data recovery capability is improved, but buffer resource availability for concurrent programming decreases
Solution Approach 1:
The buffer resources are segmented into separate user data buffer and parity data buffer, allowing independent management of each. The parity buffer, being smaller, frees up buffer resources that can be allocated to concurrent programming operations, while still maintaining data recovery capability through the stored parity information.
Solution Approach 2:
By changing from storing full user data copies to storing compact parity data, the system reduces the buffer space consumed for data protection. This parameter change increases the available buffer resources that can be simultaneously used for concurrent programming operations, improving productivity.
Data Source
AI summary
Methods, systems, and apparatuses include receiving a write command including user data. The write command is directed to a portion of memory including a first and second block and a first and second user data portion are directed to the first and second block. Temporary parity data is generated using the first and second user data portions. The temporary parity data and the first and second user data portions are stored in a buffer. Portions of the first and second block are programmed with two programming passes. The first and second user data portions in the buffer are invalidated in response to a completion of the second programming pass of the portions of the first and second blocks. The temporary parity data is maintained in the buffer until a second programming pass of the first and second block.