Dynamic Memory Bandwidth Allocation for Latency Reduction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In electronic devices, non-real time clients often experience increased memory access latency due to static memory access bandwidth allocations, leading to user-perceptible artifacts, as they compete with hard and soft real time clients for remaining bandwidth, despite having lower sensitivity to latency.
Innovation Solution
A management entity dynamically allocates and reallocates memory access bandwidth among clients, allowing non-real time clients to request and release bandwidth as needed, by temporarily reassigning bandwidth from hard and soft real time clients when necessary, ensuring efficient memory access without compromising their performance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If static memory access bandwidth allocations are used for hard and soft real time clients, then their performance is ensured, but non-real time clients experience increased latency and user-perceptible artifacts
Solution Approach 1:
The patent implements dynamic bandwidth allocation where the memory interface dynamically adjusts bandwidth allocation between hard real time clients, soft real time clients, and non-real time clients based on current system conditions. When non-real time clients have pending memory access requests and hard/soft real time clients are not currently accessing memory, the system temporarily allocates bandwidth to non-real time clients, thereby reducing their latency without compromising the guaranteed performance of hard and soft real time clients.
2Loss of time
If memory access bandwidth is allocated to non-real time clients, then latency is reduced, but available bandwidth for hard and soft real time clients decreases
Solution Approach 1:
The patent applies local quality by providing different bandwidth allocation characteristics to different client types based on their specific needs and current system state. Hard real time clients receive guaranteed bandwidth when needed, soft real time clients receive bandwidth when hard real time clients are not using it, and non-real time clients receive bandwidth during periods when neither hard nor soft real time clients require it. This localized, context-dependent allocation optimizes overall system efficiency while maintaining service quality for all client types.
Data Source
AI summary
An electronic device includes a memory; a plurality of clients; at least one arbiter circuit; and a management circuit. A given client of the plurality of clients communicates a request to the management circuit requesting an allocation of memory access bandwidth for accesses of the memory by the given client. The management circuit then determines, based on the request, a set of memory access bandwidths including a respective memory access bandwidth for each of the given client and other clients of the plurality of clients that are allocated memory access bandwidth. The management circuit next configures the at least one arbiter circuit to use respective memory access bandwidths from the set of memory access bandwidths for the given client and the other clients for subsequent accesses of the memory.