Memory Controller Safety Mode ECC Ratio Adjustment
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing memory devices with error correction codes (ECC) face challenges in maintaining operational reliability when errors exceed the ECC's correction capabilities, particularly in scenarios where DIMMs are non-replaceable or in low-cost, low-power servers, leading to potential device failure and reduced usability.
Innovation Solution
An apparatus and method that transitions from a normal mode to a safety mode by increasing the ratio of ECC symbols to data symbols in each code word, allowing continued operation with reduced data capacity but enhanced error robustness, enabling the memory device to function even when errors exceed the normal ECC correction limits.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the ratio of ECC symbols to data symbols is increased in safety mode to enhance error correction capabilities, then reliability is improved, but data storage capacity deteriorates
Solution Approach 1:
The patent implements dynamic reconfiguration of the memory device by transitioning between normal mode and safety mode. In safety mode, the ratio of ECC symbols to data symbols is increased by reducing the number of data symbols per code word while maintaining the same code word structure. This dynamic adjustment allows the system to adapt error correction capabilities to the actual error conditions observed, thereby improving reliability when needed while preserving data capacity during normal operation.
2Reliability
If redundant memory blocks are provided to maintain operation during failures, then reliability is improved, but device size and cost deteriorate
Solution Approach 1:
Instead of providing physical redundant memory blocks, the patent changes the operational parameters of the existing memory device by transitioning to safety mode. This mode involves reducing the number of data symbols per code word and increasing the proportion of ECC symbols, thereby enhancing error correction capabilities without adding any physical components. The same memory blocks are reused with modified coding parameters, avoiding the need for redundant hardware.
3Reliability
If the number of data symbols per code word is reduced in safety mode to increase ECC protection, then error robustness is improved, but productivity deteriorates
Solution Approach 1:
The patent employs feedback from error tracking circuitry that monitors the number of errors detected in read operations. When the error count exceeds a threshold, the system transitions to safety mode with reduced data symbols per code word. This feedback-driven approach ensures that the productivity reduction is only incurred when necessary, based on actual error conditions. During normal operation with low error rates, the system maintains full data capacity, thus minimizing the impact on productivity while providing error robustness when needed.
Data Source
AI summary
An apparatus includes encoding circuitry to generate code words for storage in a memory device. Decoding circuitry is responsive to a read transaction to decode one or more code words read from the memory device in order to generate read data for outputting in response to the read transaction. The decoding circuitry comprises error correction circuitry configured, for each read code word, to perform an error correction process to detect and correct errors in up to P symbols of the code word, where P is dependent on the number of ECC symbols in the code word. Error tracking circuitry determines error quantity indication data indicative of the errors detected by the error correction circuitry, and in response to the error quantity indication data indicating that an error threshold condition has been reached, the apparatus transitions from a normal mode of operation to a safety mode of operation.