Cache Controller QoS-Based Dynamic Space Allocation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In systems with shared cache memory among multiple processors, the performance is influenced by how cache memory is operated, particularly in varying quality-of-service (QoS) scenarios, where existing methods fail to dynamically allocate cache resources based on processor QoS, leading to inefficiencies and potential bottlenecks.
Innovation Solution
A cache memory system that includes a cache controller capable of storing and utilizing QoS information to dynamically allocate cache space among processors, allowing for the adjustment of cache size and entry management based on processor-specific QoS requirements, ensuring optimal resource allocation and performance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If cache memory is shared equally among multiple processors, then system simplicity is maintained, but processors with higher QoS demands experience performance bottlenecks
Solution Approach 1:
The patent applies local quality by allocating different cache space sizes to different processors based on their specific QoS requirements. Each processor receives a customized cache allocation rather than equal sharing, with high-QoS processors receiving larger allocations. This is implemented through the cache controller storing QoS information for each processor and dynamically determining cache space sizes based on these individual requirements, thereby optimizing cache hit-ratios for each processor according to its quality-of-service needs.
2Adaptability or versatility
If cache space is dynamically reallocated based on QoS information, then system adaptability improves, but control complexity increases
Solution Approach 1:
The patent applies preliminary action by pre-storing QoS information for each processor in the cache controller before cache allocation decisions are made. This allows the cache controller to quickly reference predetermined QoS parameters when processors request cache space, eliminating the need for complex real-time QoS evaluation. The QoS information is maintained in a dedicated storage unit within the cache controller, enabling efficient and adaptable cache space reallocation based on these pre-established quality-of-service parameters.
3Productivity
If fixed cache allocation is used, then system stability is maintained, but performance varies under different QoS conditions
Solution Approach 1:
The patent applies dynamics by implementing dynamic cache space allocation that adjusts cache resources based on processor QoS conditions. The cache controller continuously monitors processor requests and reallocates cache space according to stored QoS information, allowing the system to adapt to varying performance requirements. This dynamic mechanism enables high-QoS processors to receive increased cache allocation when needed, while low-QoS processors receive reduced allocation, thereby optimizing overall system performance under different quality-of-service conditions.
Data Source
AI summary
A cache memory device shared by a plurality of processors includes a cache memory configured to store some of data stored in a main memory and to be accessed by the plurality of processors. A cache controller stores quality-of-service (QoS) information of each of the plurality of processors and differently sets a size of a storage space of the cache memory to be managed by a target processor, based on the QoS information of the target processor.