Big Little Processor Switching for Network Traffic
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current Network-on-a-Chip (NoC) architectures face inefficiencies due to unnecessary switches between high-performance, high-energy 'big' processors and low-power, low-energy 'little' processors during fluctuations in network traffic, compromising energy efficiency and performance.
Innovation Solution
A method that dynamically switches between big and little processors based on data packet arrival rates and throughput thresholds, using an overflow queue managed by a token bucket algorithm to handle short bursts and optimize processor usage, thereby reducing unnecessary switches.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If the big processor is activated to handle high volume traffic, then processing performance is improved, but energy consumption increases
Solution Approach 1:
The system dynamically switches between the big processor and little processor based on real-time network traffic conditions and throughput thresholds. The big processor is activated when high volume traffic is detected and deactivated when traffic subsides, allowing the system to adapt processor capacity to actual workload demands and thereby reduce unnecessary energy consumption while maintaining performance when needed.
Solution Approach 2:
The system changes the operational state (activated/deactivated) of processors based on measurable parameters such as network traffic volume, current throughput, and sustained throughput thresholds. By monitoring these parameters and switching processors accordingly, the system optimizes the balance between processing performance and energy consumption.
2Use of energy by moving object
If the little processor is used for low volume traffic, then energy efficiency is improved, but processing capability is reduced
Solution Approach 1:
The system dynamically adjusts processor selection based on incoming traffic patterns. When network traffic volume and throughput metrics indicate low demand, the system switches to the little processor to maintain energy efficiency. When traffic spikes occur and exceed thresholds, the system transitions to the big processor to provide enhanced processing capability, thus adapting processing capacity to actual needs.
Solution Approach 2:
The overflow queue acts as an intermediary buffer between the little processor and the big processor. When the little processor is activated but traffic volume exceeds its handling capacity, the overflow queue temporarily stores packets and triggers activation of the big processor only when necessary, allowing the system to maintain energy efficiency while ensuring processing capability is available when needed.
3Adaptability or versatility
If frequent switching between processors occurs, then adaptability to traffic changes is improved, but system complexity and instability increase
Solution Approach 1:
The system implements feedback mechanisms by continuously monitoring throughput metrics and comparing them against predefined thresholds. This feedback loop enables automatic, intelligent switching between processors based on actual performance data, allowing the system to adapt to traffic changes while avoiding arbitrary or overly frequent switches through threshold-based decision making.
Solution Approach 2:
The system uses predictive thresholds and pre-configured switching criteria to anticipate when processor switching will be needed. By establishing sustained throughput thresholds and monitoring patterns in advance, the system can prepare for state changes smoothly, reducing abrupt transitions and stabilizing the system while maintaining adaptability.
Data Source
AI summary
As disclosed herein a method, executed by a computer, for providing improved multi-protocol traffic processing includes receiving a data packet, determining if a big processor is activated, deactivating a little processor and activating the big processor if the big processor is not activated and an overflow queue is full, and deactivating the big processor and activating the little processor if the big processor is activated and a current throughput for the big processor is below a first threshold or a sustained throughput for the big processor remains below a second threshold. The big and little processors may be co-located on a single integrated circuit. An overflow queue, managed with a token bucket algorithm, may be used to enable the little processor to handle short burst of data packet traffic. A computer program product and an apparatus corresponding to the described method are also disclosed herein.