Dynamic Token Rate Control for Memory Bus Bandwidth Efficiency
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing information processing technologies face inefficiencies in using bus bandwidths, leading to latency and hindered real-time responses due to the allocation of processing time and memory, especially when handling multiple tasks that require high-speed data transmission.
Innovation Solution
An information processing apparatus that includes requester units, an issuance rate control part, and an access processing part to manage access requests based on implemented bus bandwidth, allowing for adaptive and efficient use of bus resources by adjusting token generation rates and issuance limits to optimize data transmission.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of energy
If tokens are granted at predetermined rates to control bus bandwidth usage, then bus bandwidth efficiency is improved, but processing latency increases due to token acquisition delays
Solution Approach 1:
The patent applies dynamics by making the token grant rate adjustable rather than fixed. The determination unit dynamically changes the token grant rate based on the current bus utilization state. When bus utilization is low, the token grant rate is increased to reduce latency; when bus utilization is high, the rate is decreased to maintain bandwidth efficiency. This dynamic adjustment resolves the contradiction between bandwidth efficiency and processing latency.
Solution Approach 2:
The patent changes the parameter of token grant rate based on bus utilization conditions. The determination unit monitors bus utilization and adjusts the token grant rate parameter accordingly. This parameter change allows the system to optimize both bandwidth efficiency and latency by adapting to real-time conditions, rather than being constrained by a predetermined fixed rate.
2Adaptability or versatility
If multiple applications share bus bandwidth through time-division multiplexing, then system adaptability is improved, but real-time response performance deteriorates when other applications consume excessive bandwidth
Solution Approach 1:
The patent implements feedback by having the determination unit continuously monitor bus utilization and use this information to adjust token grant rates. This feedback mechanism ensures that real-time applications can receive increased bandwidth allocation when the bus is underutilized, while still maintaining overall system adaptability for multiple applications. The feedback loop prevents any single application from monopolizing the bus and degrading real-time performance.
Data Source
AI summary
Requestors acquire tokens before issuing access requests to a memory controller. The access requests issued are accumulated in a command queue of the memory controller. When the amount of access requests accumulated in the command queue is smaller than or equal to a first threshold, or in level 0, tokens are generated at a rate equivalent to 200% of a bus bandwidth. If the amount of accumulation is greater than the first threshold and is smaller than or equal to a second threshold, i.e., in level 1, tokens are generated at a rate equivalent to the bus bandwidth. If the amount of accumulation exceeds the second threshold, the token generation is stopped.


