Memory Controller Error Correction With Adaptive Power Search
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The increased integrity and introduction of multi-level cells (MLCs) in semiconductor memory devices lead to higher error rates, necessitating additional error correcting logic, which in turn increases power consumption.
Innovation Solution
A memory controller method that adjusts power consumption based on the number of errors in a read vector by selectively conducting error searches on either the data or parity portions, using syndrome codes and error location polynomials to determine the number of errors and optimize the search process.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If error correcting logic is added to handle increased error rates from improved integrity and MLC, then data reliability is improved, but power consumption increases
Solution Approach 1:
The patent implements dynamic power consumption adjustment in the error correction process. The controller varies power consumption levels based on the actual error rate detected in read vectors, transitioning between different operational modes (normal mode for high error rates, power-saving mode for low error rates) to optimize the balance between reliability and energy usage.
Solution Approach 2:
The patent changes operational parameters of the error correction logic based on detected error conditions. By monitoring the number of errors in read vectors and comparing against thresholds, the system adjusts parameters such as power consumption levels and error correction intensity to match actual data quality, avoiding unnecessary full-power correction operations.
2Measurement precision
If full error search is conducted on entire read vector including parity portion, then error detection accuracy is improved, but power consumption increases
Solution Approach 1:
The patent segments the error search process into different portions of the read vector. The search can be limited to only the data portion or extended to include the parity portion based on error conditions. This segmentation allows the system to perform comprehensive error detection when needed while reducing unnecessary searches in low-error scenarios.
Solution Approach 2:
The patent applies partial error search action by conducting error detection only on necessary portions of the read vector. When error rates are low, the system performs partial searching (data portion only) rather than exhaustive searching (entire read vector), achieving sufficient error detection with reduced energy expenditure.
Data Source
AI summary
A method of operating a memory controller to control a memory device includes reading a read vector from the memory device and correcting one or more errors in the read vector, where a power consumed at the correcting is varied according to the number of errors in the read vector.