Adaptive Memory Scheduling Queue Control via Page Hit Distance
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing memory controller solutions, such as DRAM controllers, face performance inefficiencies due to their inability to adaptively manage scheduling queue occupancy based on actual workload characteristics, leading to increased latency and reduced memory access speed.
Innovation Solution
Implementing an adaptive scheduling queue control mechanism that adjusts the number of access requests stored in the scheduling queue based on page hit distance determinations, using a threshold occupancy value calculated from historical data to prioritize page hits and optimize SQ occupancy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If access requests are throttled to increase scheduling queue occupancy, then page hit rate is improved, but memory access speed and efficiency are reduced
Solution Approach 1:
The patent implements dynamic adjustment of the scheduling queue occupancy threshold based on runtime workload characteristics. The threshold is not fixed but adapts to changing conditions, allowing the system to optimize between page hit rate and memory access speed depending on the current workload pattern. This resolves the contradiction by making the throttling mechanism adaptive rather than static.
Solution Approach 2:
The patent changes the parameter of scheduling queue occupancy threshold from a predetermined fixed value to a dynamically adjusted value based on page hit distance measurements. By monitoring actual workload characteristics and adjusting the threshold parameter accordingly, the system can achieve high page hit rates without the performance degradation caused by excessive throttling.
2Quantity of substance
If a fixed delay timer is used for throttling, then scheduling queue occupancy is increased, but adaptability to actual workload characteristics is lost
Solution Approach 1:
The patent introduces a feedback mechanism that monitors page hit distance for actual memory access requests and uses this information to dynamically adjust the scheduling queue occupancy threshold. This feedback loop enables the system to adapt to real workload characteristics rather than relying on predetermined fixed delays, resolving the contradiction between maintaining queue occupancy and achieving workload adaptability.
Solution Approach 2:
The system performs self-adjustment by automatically monitoring its own performance metrics (page hit distance) and using this information to tune its own scheduling parameters. This self-service approach eliminates the need for external configuration or fixed timers, allowing the system to autonomously adapt to varying workload conditions while maintaining appropriate queue occupancy.
Data Source
AI summary
Methods and systems are disclosed for adaptive scheduling queue control based upon page hit distance determinations. A threshold occupancy value is determined for a window of previous access requests to a memory and used to adaptively control a number of access requests stored in a scheduling queue buffer. For certain embodiments, a page hit distance (PHD) determination for each access request and historical page hit distance data is used to adjust the threshold occupancy value that determines the number (N) of access requests stored in the buffer prior to removing an access request and using it to access the memory. For each access request, the page hit distance represents the number of previously received access requests since the last access request to access the same page of memory. An average PHD can be determined over a number (M) of previous access requests and used to control the threshold occupancy value.