Dynamic Memory Refresh Rate Adjustment for Error Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Cloud computing facilities face significant energy consumption and operational costs due to the power required for computing resources and cooling, with existing methods to reduce memory errors often increasing power usage and decreasing system performance.
Innovation Solution
Implement a dynamic adjustment of the refresh rate and patrol scrub rate of memory based on detected error rates, allowing for increased protection during high error rates and reduced power consumption when errors are within a desired range, without interrupting system services.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the refresh rate and patrol scrub rate are increased to reduce memory errors, then memory reliability is improved, but power consumption increases
Solution Approach 1:
The patent implements dynamic adjustment of refresh rate and patrol scrub rate based on real-time error rate monitoring. The system transitions from static, fixed rates to dynamic, adaptive rates that change according to actual memory conditions. This resolves the contradiction by only increasing power consumption when error rates warrant it, rather than maintaining high rates continuously.
Solution Approach 2:
The system changes operational parameters (refresh rate and patrol scrub rate) based on detected error rates. When error rates exceed thresholds, the system increases these parameters to improve reliability; when error rates are acceptable, it decreases them to reduce power consumption. This parameter adaptation resolves the contradiction between reliability and energy use.
2Reliability
If the refresh rate is increased to protect against memory errors, then memory protection is improved, but system performance decreases
Solution Approach 1:
The patent makes the refresh rate and patrol scrub rate dynamic rather than static. The system adjusts these rates in real-time based on monitored error rates, increasing protection only when errors are detected and reducing it when the memory is stable. This dynamic approach maintains system performance while providing adequate protection.
Solution Approach 2:
The system applies memory protection at partial or excessive levels only when necessary. Instead of continuously applying maximum protection, the system monitors error rates and applies increased refresh and scrub rates only when error thresholds are exceeded, thus maintaining performance while providing adequate protection when needed.
3Reliability
If static high refresh rates are used to ensure memory reliability, then memory errors are reduced, but operational costs increase
Solution Approach 1:
The patent implements a feedback mechanism where the system continuously monitors memory error rates and uses this information to adjust refresh and patrol scrub rates. This closed-loop control ensures memory reliability is maintained through feedback-driven adaptation, reducing operational costs by avoiding unnecessary high-rate operations when errors are not present.
Solution Approach 2:
The system performs self-adjustment of memory protection parameters based on its own monitored error rates. The memory subsystem serves itself by autonomously adjusting refresh and scrub rates according to its actual condition, eliminating the need for static over-protection and reducing operational costs while maintaining reliability.
Data Source
AI summary
The following description is directed to dynamically adjusting a refresh rate. In one example, a method can include determining a rate of memory errors, and dynamically adjusting a refresh rate of a memory based at least partially on the determined rate of memory errors.