Memory Block Retirement Using Temperature and Error Criteria
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing memory systems face issues with overly conservative techniques for retiring memory blocks, leading to excessive retirement and reduced capacity or lifespan due to unreliable access operations.
Innovation Solution
A memory system that determines the occurrence of errors in blocks based on multiple operating conditions, such as temperature, cycle count, error rate, and available blocks, to selectively retire blocks more or less aggressively, thereby optimizing capacity and lifespan.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If memory blocks are retired based on unreliable access operations, then reliability is improved, but memory capacity and lifespan deteriorate due to excessive retirement
Solution Approach 1:
The patent changes the parameters used for retirement decisions from simple access operation reliability to a multi-dimensional assessment including temperature, cycle count, error rate, and available block count. This allows the system to adjust retirement aggressiveness based on current operating conditions, retiring blocks only when multiple criteria indicate genuine degradation rather than temporary failures.
Solution Approach 2:
The retirement policy is made dynamic rather than static. The system continuously monitors operating conditions and adjusts its retirement strategy in real-time, being more conservative when temperature is high or cycle count is low, and more aggressive when error rates are consistently high and alternative blocks are available. This dynamic approach prevents premature retirement while maintaining reliability.
2Reliability
If memory blocks are retired based on unreliable access operations, then reliability is improved, but device lifespan deteriorates
Solution Approach 1:
The patent introduces cycle count as a key parameter in retirement decisions, preventing blocks from being retired prematurely based on transient errors. By requiring multiple failure criteria to be met simultaneously (high error rate, high temperature, high cycle count), the system extends the operational lifespan of memory blocks while still retiring them when genuine degradation occurs.
Solution Approach 2:
The system implements continuous feedback monitoring of temperature, cycle count, and error rates to make informed retirement decisions. This feedback mechanism allows the system to learn from operating patterns and adjust retirement timing, extending lifespan by avoiding retirement during temporary degradation while capturing blocks when permanent failure is imminent.
3Quantity of substance
If memory blocks are retired conservatively, then memory capacity is preserved, but reliability deteriorates due to continued use of degraded blocks
Solution Approach 1:
The patent transforms the retirement decision from a binary conservative/aggressive choice to a multi-parameter assessment. By evaluating temperature, cycle count, error rate, and available block count simultaneously, the system achieves optimal retirement timing that preserves capacity while maintaining reliability, retiring blocks only when multiple indicators confirm genuine degradation.
4Measurement precision
If multiple operating conditions are monitored for retirement decisions, then retirement precision is improved, but device complexity increases
Solution Approach 1:
The patent monitors multiple parameters (temperature, cycle count, error rate, available blocks) but uses a rule-based decision framework that evaluates these parameters through simple threshold comparisons and logical operators. This approach achieves high retirement decision accuracy without requiring complex machine learning models or sophisticated algorithms, maintaining relatively simple device architecture.
Data Source
AI summary
Methods, systems, and devices for techniques for retiring blocks of a memory system are described. In some examples, aspects of a memory system or memory device may be configured to determine an error for a block of memory cells. Upon determining the occurrence of the error, the memory system may identify one or more operating conditions associated with the block. For example, the memory system may determine a temperature of the block, a cycle count of the block, a quantity of times the block has experienced an error, a bit error rate of the block, and/or a quantity of available blocks in the associated system. Depending on whether a criteria associated with a respective operating condition is satisfied, the block may be enabled or retired.