Inline Error Detection Circuitry for Memory Arrays
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Integrated circuits, particularly memory arrays, are vulnerable to soft errors where data bits can be incorrectly read due to bit flips, especially as process geometries shrink and array sizes decrease, necessitating effective error detection and correction mechanisms.
Innovation Solution
Incorporation of inline error detection circuitry, such as inline parity checking and ECC detection circuitry, which generates flag bits and ECC check bits to detect and correct bit errors in real-time, allowing for continuous monitoring and correction of errors without the need for read operations, thereby optimizing time and reducing power consumption.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If memory arrays are shrunk in size and process geometries are reduced, then integration density and capacity are improved, but vulnerability to soft errors and bit flips increases
Solution Approach 1:
The patent applies preliminary action by performing error detection continuously in the background before read operations are needed. The inline error detection circuitry monitors data bits as they are written to memory cells and generates flag bits indicating potential errors, so that when a read operation occurs, the error is already detected and can be handled immediately, preventing error accumulation.
Solution Approach 2:
The patent uses flag bits as intermediary elements between the data bits stored in memory cells and the error detection mechanism. These flag bits are generated by inline error detection circuitry and serve as intermediaries that carry error information without requiring additional read operations on the actual data bits, thus enabling error detection while maintaining the integrity and speed of memory access.
2Reliability
If error detection circuitry is added to memory arrays, then error detection capability is improved, but device complexity and area increase
Solution Approach 1:
The patent merges error detection functionality directly into the memory array structure by placing error detection circuitry inline with the memory cells. This integration allows the error detection circuitry to share physical space and operational pathways with the data storage elements, reducing overall device complexity compared to separate error detection systems.
Solution Approach 2:
The patent segments the error detection function into individual inline detection units associated with specific memory cells or groups of cells. Each segment can independently generate flag bits for its associated data bits, allowing distributed error detection that reduces the complexity burden on any single part of the system and enables modular design.
3Reliability
If traditional error detection is performed at read ports, then error detection is achieved, but time consumption and power usage increase due to additional read operations
Solution Approach 1:
The patent performs error detection in advance during write operations or in continuous background mode, so that by the time a read operation is needed, the error status is already known via pre-generated flag bits. This eliminates the need to perform additional read operations solely for error detection, saving time and reducing power consumption.
Solution Approach 2:
The memory array becomes self-service regarding error detection, as the inline error detection circuitry automatically monitors data bits and generates flag bits without requiring external control signals or additional read operations. The system detects and reports errors autonomously as part of its normal operation.
Data Source
AI summary
Various implementations described herein may refer to and may be directed to error detection circuitry for use with memory. In one implementation, an integrated circuit may include a memory array having a plurality of rows of memory cells, where a respective row is configured to store a data word and one or more check bits corresponding to the data word. The integrated circuit may also include inline error detection circuitry coupled to the respective row and configured to generate one or more flag bit values based on a detection of one or more bit errors in the data word stored in the respective row. The integrated circuit may further include error correction circuitry configured to correct the one or more bit errors in the data word stored in the respective row in response to the one or more generated flag bit values.